Re: [R] Re: Reasons not to answer very basic questions...
Jim Lemon wrote: A.J. Rossini wrote: and perhaps the most important reason for the particular socratic form of teaching on this list... Golly, anyone who read Plato's Dialogues would realize that the Socratic method involves patiently leading the questioner stepwise through the solution, not simply writing RTFMeno. Jim Jim, yes, that way works as long as the number of questioners does not sum up to a lot: It is easy to teach courses for 20 people and answer individual questions, even if these questions are very basic and have been explained more than once during the course. Courses for 700 people (e.g. basic statistics for economists) in the biggest auditory aren't that funny and you have to say read what I/others have written! - or next month almost each student will be in your office asking question he/she could not work out in half an hour him/herself ... So it is my very serious opinion that we need to point people to the basic documentation and the FAQ, if they post their first very basic question to the list. If the questioner asks the next basic questions as well, and with him many others, we will have a flood of many hundreds of messages a day! Uwe __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] about cancor.R
Hello, I'm a beginning user of R, now I have a question about canonical correlation analysis (cca). In R,there is a function cancor.R used for cca; For example X(n*p1) and Y(n*p2)are the two matrix to be analyzed. In the example given by R, when n max(p1,n2), cancor(X,Y) works; but when np1 or np2, cancor(X,Y) doesn't work well because cancor$cor == 1; how to cope with this case? maybe before apply the two matrix to cancor.R, some time-space transformation should be done? could you give some suggestion? Thanks you in advance! Best regards, Yan ZHAO __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] about cancor.R
On Tue, 30 Nov 2004, yan zhao wrote: Hello, I'm a beginning user of R, now I have a question about canonical correlation analysis (cca). In R,there is a function cancor.R used for cca; For example There is no such function in R, and I can't find it in any add-on package. Do you mean the function cancor() in the stats package? X(n*p1) and Y(n*p2)are the two matrix to be analyzed. In the example given by R, when n max(p1,n2), cancor(X,Y) works; but when np1 or np2, cancor(X,Y) doesn't work well because cancor$cor == 1; how to cope with this case? maybe before apply the two matrix to cancor.R, some time-space transformation should be done? could you give some suggestion? Thanks you in advance! You need to understand the underlying theory: the problem is not with the function but your use of the technique. Assuming non-degenerate matrices, you have a situation in which one of the matrices spans the entire space of observations and so imposes no restriction. R help pages come with references: please consult them. Since you have not told us why you are using CCA, we can't help you with the methodological questions, even if they are off topic for the R-help list. -- Brian D. Ripley, [EMAIL PROTECTED] Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/ University of Oxford, Tel: +44 1865 272861 (self) 1 South Parks Road, +44 1865 272866 (PA) Oxford OX1 3TG, UKFax: +44 1865 272595 __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: Re: [R] systemfit - SUR
Arne Henningsen [EMAIL PROTECTED] schrieb am 29.11.2004, 17:02:12: On Monday 29 November 2004 16:42, [EMAIL PROTECTED] wrote: Hello to everyone, I have 2 problems and would be very pleased if anyone can help me: 1) When I use the package systemfit for SUR regressions, I get two different variance-covariance matrices when I firstly do the SUR regression (The covariance matrix of the residuals used for estimation) and secondly do the OLS regressions. In the manual for systemfit on page 14 I see however, that the variance-covariance matrix for SUR is obtained from OLS. How can this be explained? Hi Thomas, I get identical residual covariance matrices: R library(systemfit) R data( kmenta ) R demand supply labels system fitols fitols$rcov [,1] [,2] [1,] 3.725391 4.136963 [2,] 4.136963 5.784441 R fitsur fitsur$rcovest [,1] [,2] [1,] 3.725391 4.136963 [2,] 4.136963 5.784441 It is a pity, but my matrices are not as nice :-( An excerpt: fitsur$rcovest [,1] [,2] [,3] ... [1,] 0.015097517 0.018005050 [2,] 0.018005050 0.276259834 ... fitols$rcov [,1] [,2] [,3] ... [1,] 1.010326e-02 0.0096103837 [2,] 9.610384e-03 0.2329884378 ... fitsur The covariance matrix of the residuals used for estimation: eq1 eq2eq3 ... eq1 0.01317429 0.01504719 0.007981307 eq2 0.01504719 0.25233860 ... fitols The covariance matrix of the residuals: eq1 eq2 eq3 ... eq1 9.51154e-03 0.009137884 0.002648577 eq2 9.13788e-03 0.220435063 ... By the way: Why are the figures larger for SUR? Did you do _iterated_ SUR? Yes: systemfit results method: iterated SUR convergence achieved after 30 iterations I do not know how to change that. Best wishes, Arne THANKS A LOT FOR YOUR IMMEDIATE HELP!!! 2) Is there an easy possibility to test a) the OLS equations, and b) the SUR system for SUR structures? In other words: Is the LM-Test from Breusch and Pagan available in R? Thanks for the attention! Best Regards, Thomas Almer __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html -- Arne Henningsen Department of Agricultural Economics University of Kiel Olshausenstr. 40 D-24098 Kiel (Germany) Tel: +49-431-880 4445 Fax: +49-431-880 1397 [EMAIL PROTECTED] http://www.uni-kiel.de/agrarpol/ahenningsen/ __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Problem with print() and backslashes.
Dear R List I have a small problem concerning the output of print(). My version: R.version _ platform i386-portbld-freebsd5.2 arch i386 os freebsd5.2 system i386, freebsd5.2 status major1 minor9.0 year 2004 month04 day 12 language R Consider this: I want to print a backslash with an exclamation mark. Here is the output. print( \! ) [1] ! Now I try it differently... print( \\! ) [1] \\! The output contains two backslashes. Why? Regards, Kevin __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Problem with print() and backslashes.
On Tue, 30 Nov 2004, Kevin Brinkmann wrote: Dear R List I have a small problem concerning the output of print(). My version: R.version _ platform i386-portbld-freebsd5.2 arch i386 os freebsd5.2 system i386, freebsd5.2 status major1 minor9.0 year 2004 month04 day 12 language R Consider this: I want to print a backslash with an exclamation mark. Here is the output. print( \! ) [1] ! Now I try it differently... print( \\! ) [1] \\! The output contains two backslashes. Why? Because it is documented to escape backslashes: use cat() if that is not what you want. -- Brian D. Ripley, [EMAIL PROTECTED] Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/ University of Oxford, Tel: +44 1865 272861 (self) 1 South Parks Road, +44 1865 272866 (PA) Oxford OX1 3TG, UKFax: +44 1865 272595 __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Problem with print() and backslashes.
Kevin Brinkmann [EMAIL PROTECTED] writes: Consider this: I want to print a backslash with an exclamation mark. Here is the output. print( \! ) [1] ! Now I try it differently... print( \\! ) [1] \\! The output contains two backslashes. Why? (Didn't we do that one only yesterday?) The answer is: For the same reason that you need them on input. R likes to line things up in columns when printing vectors so cannot just print special characters like newline, carriage return, etc. Instead it represents them as \n, \r just like on input. To distinguish from backslash-followed-by-n the backslash is itself escaped with a backslash. Use cat() to output a string as raw characters. -- O__ Peter Dalgaard Blegdamsvej 3 c/ /'_ --- Dept. of Biostatistics 2200 Cph. N (*) \(*) -- University of Copenhagen Denmark Ph: (+45) 35327918 ~~ - ([EMAIL PROTECTED]) FAX: (+45) 35327907 __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
RE: [R] Problem with print() and backslashes.
-Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Kevin Brinkmann Sent: Tuesday, November 30, 2004 9:43 AM To: [EMAIL PROTECTED] Subject: [R] Problem with print() and backslashes. Dear R List I have a small problem concerning the output of print(). snip/snip Consider this: I want to print a backslash with an exclamation mark. Here is the output. print( \! ) [1] ! Now I try it differently... print( \\! ) [1] \\! The output contains two backslashes. Why? cat(\\!) \! also str(\\!) chr \! What is important to keep in mind is that the string \\! has *two* characters (when read by R), not three (as on the screen or in your editor); nchar(\\!) [1] 2 The first character is \\, which needs to be escaped in order for the R parser to recognize it as '\'. The second is of course '!'. I agree that nchar(\!) [1] 1 might be confusing. The thing is that some characters remain the same escaped or not, whereas others have certain mappings to non-printable ASCII codes (0-255). identical(\!, !) [1] TRUE and the well known(?) newline character identical(\n, n) [1] FALSE Another good example: identical(\, '') [1] TRUE Given a string, print() gives you the escaped version of the string, which can be useful for debugging, if you want to cut'n'paste and so on. Thus, print(Hello world\n!\n) [1] Hello world\n!\n and cat(Hello world\n!\n) Hello world ! Hope this helps! Henrik Bengtsson Regards, Kevin __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Creating a factor from a combination of vectors
Dear list, Here's a little problem I already solved with my own coding style, but I feel there is a more efficient and cleaner way to write it, but had no success finding the clever solution. I want to produce a factor from a subset of the combination of two vectors. I have the vectors a et b in a data-frame : df - expand.grid(a=c(0, 5, 10, 25, 50), b=c(0, 25, 50, 100, 200)) fac.df a b 1 0 0 2 5 0 3 10 0 4 25 0 5 50 0 6 0 25 7 5 25 snip and want to create a factor which levels correspond to particular combinations of a and b (let's say Low for a=0 b=0, Medium for a=10 b=50, High for a=50 b=200, others levels set to NA), reading them from a data-frame which describes the desired subset and corresponding levels. Here's my own solution (inputs are data-frames df and cas, output is the sub factor): cas - as.data.frame(matrix(c(0, 10,50, 0, 50, 200), 3, 2,dimnames=list(c(Low, Medium, High), c(a, b cas a b Low 0 0 Medium 10 50 High 50 200 sub - character(length(df$a)) for (i in 1:length(df$a)) { + temp - rownames(cas)[cas$a==df$a[i] cas$b==df$b[i]] + sub[i] - ifelse(length(temp)0, temp, NA) + } sub - ordered(sub, levels=c(Low, Medium, High)) sub [1] LowNA NA NA NA NA NA NA NA NA NA NA Medium NA NA NA NA [18] NA NA NA NA NA NA NA High Levels: Low Medium High I was looking for a vectorized solution (apply style) binding data-frames df and cas, but didn't succeed avoiding the for loop. Could anybody bring me the ligths over the darkness of my ignorance ? Thank you very much in advance. -- Ir. Yves BROSTAUX Unité de Statistique et Informatique Faculté universitaire des Sciences agronomiques de Gembloux (FUSAGx) 8, avenue de la Faculté B-5030 Gembloux Belgique Tél: +32 81 62 24 69 Email: [EMAIL PROTECTED] __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] systemfit - SUR
On Tuesday 30 November 2004 09:34, [EMAIL PROTECTED] wrote: Arne Henningsen [EMAIL PROTECTED] schrieb am 29.11.2004, 17:02:12: On Monday 29 November 2004 16:42, [EMAIL PROTECTED] wrote: Hello to everyone, I have 2 problems and would be very pleased if anyone can help me: 1) When I use the package systemfit for SUR regressions, I get two different variance-covariance matrices when I firstly do the SUR regression (The covariance matrix of the residuals used for estimation) and secondly do the OLS regressions. In the manual for systemfit on page 14 I see however, that the variance-covariance matrix for SUR is obtained from OLS. How can this be explained? Hi Thomas, I get identical residual covariance matrices: R library(systemfit) R data( kmenta ) R demand supply labels system fitols fitols$rcov [,1] [,2] [1,] 3.725391 4.136963 [2,] 4.136963 5.784441 R fitsur fitsur$rcovest [,1] [,2] [1,] 3.725391 4.136963 [2,] 4.136963 5.784441 It is a pity, but my matrices are not as nice :-( Please show how you obtained these results. This is what I did: R data( kmenta ) R demand - q ~ p + d R supply - q ~ p + f + a R labels - list( demand, supply ) R system - list( demand, supply ) R R # OLS estimation: R fitols - systemfit(OLS, system, labels, data=kmenta ) R # (non-iterated) SUR estimation R fitsur - systemfit(SUR, system, labels, data=kmenta ) R iterated SUR estimation R fitsurit - systemfit(SUR, system, labels, data=kmenta, maxit=100 ) R R fitols$rcov [,1] [,2] [1,] 3.725391 4.136963 [2,] 4.136963 5.784441 R fitsur$rcovest [,1] [,2] [1,] 3.725391 4.136963 [2,] 4.136963 5.784441 R fitsurit$rcovest [,1] [,2] [1,] 6.199071 7.493383 [2,] 7.493383 9.128547 An excerpt: fitsur$rcovest [,1] [,2] [,3] ... [1,] 0.015097517 0.018005050 [2,] 0.018005050 0.276259834 ... fitols$rcov [,1] [,2] [,3] ... [1,] 1.010326e-02 0.0096103837 [2,] 9.610384e-03 0.2329884378 ... fitsur The covariance matrix of the residuals used for estimation: eq1 eq2eq3 ... eq1 0.01317429 0.01504719 0.007981307 eq2 0.01504719 0.25233860 ... fitols The covariance matrix of the residuals: eq1 eq2 eq3 ... eq1 9.51154e-03 0.009137884 0.002648577 eq2 9.13788e-03 0.220435063 ... By the way: Why are the figures larger for SUR? OLS minimizes the residuals and, thus, also the variance of the residuals (=diagonal of the residual covariance matrix). Iterated SUR is equivalent to a maximum likelihood estimation. Maximizing the likelihood value is equivalent to minimizing the determinant of the residual covariance matrix. Thus, the determinant of the residual covariance matrix and not the residuals itself are minimized: R det(fitols$rcov) [1] 4.434845 R det(fitsurit$rcov) [1] 0.4376941 R det(fitsurit$rcovest) [1] 0.4377184 Did you do _iterated_ SUR? Yes: systemfit results method: iterated SUR convergence achieved after 30 iterations If you use iterated SUR, the SUR estimations are iterated. In the first SUR estimation the residual covariance matrix of the OLS estimation is used. In all following iterations the residual covariance matrix of the previous step SUR estimation is used. I do not know how to change that. Please read the documentation. It says to set argument maxit to 1 - or do not provide this argument, since 1 is the default. Best wishes, Arne THANKS A LOT FOR YOUR IMMEDIATE HELP!!! 2) Is there an easy possibility to test a) the OLS equations, and b) the SUR system for SUR structures? In other words: Is the LM-Test from Breusch and Pagan available in R? I don't understand what you want to test. Does the hausman test what you are looking for (see ?hausman.systemfit). If you have questions regarding this test, you might ask my co-author of systemfit, Jeff Hamann. Best wishes, Arne Thanks for the attention! Best Regards, Thomas Almer __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html -- Arne Henningsen Department of Agricultural Economics University of Kiel Olshausenstr. 40 D-24098 Kiel (Germany) Tel: +49-431-880 4445 Fax: +49-431-880 1397 [EMAIL PROTECTED] http://www.uni-kiel.de/agrarpol/ahenningsen/ __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html -- Arne Henningsen Department of Agricultural Economics University of Kiel Olshausenstr. 40 D-24098 Kiel (Germany) Tel: +49-431-880 4445 Fax: +49-431-880 1397 [EMAIL PROTECTED]
Re: Re: [R] systemfit - SUR
Arne Henningsen [EMAIL PROTECTED] schrieb am 30.11.2004, 10:20:29: On Tuesday 30 November 2004 09:34, [EMAIL PROTECTED] wrote: Arne Henningsen schrieb am 29.11.2004, 17:02:12: On Monday 29 November 2004 16:42, [EMAIL PROTECTED] wrote: Hello to everyone, I have 2 problems and would be very pleased if anyone can help me: 1) When I use the package systemfit for SUR regressions, I get two different variance-covariance matrices when I firstly do the SUR regression (The covariance matrix of the residuals used for estimation) and secondly do the OLS regressions. In the manual for systemfit on page 14 I see however, that the variance-covariance matrix for SUR is obtained from OLS. How can this be explained? Hi Thomas, I get identical residual covariance matrices: R library(systemfit) R data( kmenta ) R demand supply labels system fitols fitols$rcov [,1] [,2] [1,] 3.725391 4.136963 [2,] 4.136963 5.784441 R fitsur fitsur$rcovest [,1] [,2] [1,] 3.725391 4.136963 [2,] 4.136963 5.784441 It is a pity, but my matrices are not as nice :-( Please show how you obtained these results. I did not provide the steps, because the data is not public. But that is what I did after defining the system and labels (like you the documentation): fitols-systemfit(OLS, system, labels) fitsur-systemfit(SUR, system, labels, maxit=100) But after all I think your answers are sufficient. Thanks once again for your support. R and the community are really excellent and a big thread to competitors! This is what I did: R data( kmenta ) R demand supply labels system R # OLS estimation: R fitols # (non-iterated) SUR estimation R fitsur iterated SUR estimation R fitsurit R fitols$rcov [,1] [,2] [1,] 3.725391 4.136963 [2,] 4.136963 5.784441 R fitsur$rcovest [,1] [,2] [1,] 3.725391 4.136963 [2,] 4.136963 5.784441 R fitsurit$rcovest [,1] [,2] [1,] 6.199071 7.493383 [2,] 7.493383 9.128547 An excerpt: fitsur$rcovest [,1] [,2] [,3] ... [1,] 0.015097517 0.018005050 [2,] 0.018005050 0.276259834 ... fitols$rcov [,1] [,2] [,3] ... [1,] 1.010326e-02 0.0096103837 [2,] 9.610384e-03 0.2329884378 ... fitsur The covariance matrix of the residuals used for estimation: eq1 eq2eq3 ... eq1 0.01317429 0.01504719 0.007981307 eq2 0.01504719 0.25233860 ... fitols The covariance matrix of the residuals: eq1 eq2 eq3 ... eq1 9.51154e-03 0.009137884 0.002648577 eq2 9.13788e-03 0.220435063 ... By the way: Why are the figures larger for SUR? OLS minimizes the residuals and, thus, also the variance of the residuals (=diagonal of the residual covariance matrix). Iterated SUR is equivalent to a maximum likelihood estimation. Maximizing the likelihood value is equivalent to minimizing the determinant of the residual covariance matrix. Thus, the determinant of the residual covariance matrix and not the residuals itself are minimized: R det(fitols$rcov) [1] 4.434845 R det(fitsurit$rcov) [1] 0.4376941 R det(fitsurit$rcovest) [1] 0.4377184 Did you do _iterated_ SUR? Yes: systemfit results method: iterated SUR convergence achieved after 30 iterations If you use iterated SUR, the SUR estimations are iterated. In the first SUR estimation the residual covariance matrix of the OLS estimation is used. In all following iterations the residual covariance matrix of the previous step SUR estimation is used. I do not know how to change that. Please read the documentation. It says to set argument maxit to 1 - or do not provide this argument, since 1 is the default. Best wishes, Arne THANKS A LOT FOR YOUR IMMEDIATE HELP!!! 2) Is there an easy possibility to test a) the OLS equations, and b) the SUR system for SUR structures? In other words: Is the LM-Test from Breusch and Pagan available in R? I don't understand what you want to test. Does the hausman test what you are looking for (see ?hausman.systemfit). If you have questions regarding this test, you might ask my co-author of systemfit, Jeff Hamann. Primarily I want to test if the variance covariance matrix of the OLS residuals is diagonal. But this can be done manually, of course. Best wishes, Arne Thanks for the attention! Best Regards, Thomas Almer __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html -- Arne Henningsen Department of Agricultural Economics University of Kiel Olshausenstr. 40 D-24098 Kiel (Germany) Tel: +49-431-880 4445 Fax: +49-431-880
Re: [R] plotting data in non-orthogonal coords.
Am Dienstag, 30. November 2004 10:26 schrieb Petr Pikal: Hallo Andreas There is probably no one who can give you some answer as you did provide almost no facts what you really did and what is wrong. You probably need to transform your coordinates to orthogonal and plot them as you wish. But you have to do it yourself. I had some data in polar coordinates some time ago and I did the same (see attached picture). Cheers Petr On 29 Nov 2004 at 14:29, Andreas Franke wrote: Hi ! I am wondering how to plot data (e.g. f(x,y) ) in a coordinate system spanned by two non-orthogonal basis vectors (e.g. hexagonal symmetry). The data is given on an equally spaced grid in theses coords and i would like to do a contour plot (e.g. with filled.contour). Thanks for your help. Andreas __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html Petr Pikal [EMAIL PROTECTED] Hi ! Thanks for replying to my post and sorry for not being specific enough. Maybe I am the one who didnt get the point , but as far as I understand R plots filled.contour(x,y,z,...) in the following way: x,y define a grid in cartesian coords, i.e. the angle between x and y is 90°. So if I have data on such a grid I am fine. My data is on an equally spaced grid in a coordsystem where x and y are at an angle of 60°. If you transform into cartesiancoords this isnt an equally spaced grid anymore. You could interpret it as an equally spaced grid on which there is only data given on every second grid point. It would be nice if one could just plot data given as F(x,y) where you supply x and y for every data point seperatly so that you dont need any specific grid. I hope that someone can help. Thanks in advance. Andreas __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] plotting data in non-orthogonal coords.
Hallo Andreas There is probably no one who can give you some answer as you did provide almost no facts what you really did and what is wrong. You probably need to transform your coordinates to orthogonal and plot them as you wish. But you have to do it yourself. I had some data in polar coordinates some time ago and I did the same (see attached picture). Cheers Petr On 29 Nov 2004 at 14:29, Andreas Franke wrote: Hi ! I am wondering how to plot data (e.g. f(x,y) ) in a coordinate system spanned by two non-orthogonal basis vectors (e.g. hexagonal symmetry). The data is given on an equally spaced grid in theses coords and i would like to do a contour plot (e.g. with filled.contour). Thanks for your help. Andreas __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html Petr Pikal [EMAIL PROTECTED] __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] systemfit - SUR
On Tuesday 30 November 2004 10:50, [EMAIL PROTECTED] wrote: [ . . .] Please show how you obtained these results. I did not provide the steps, because the data is not public. A general remark: In most cases a questioner can use the example data provided with a package or construct simple data, e.g. with matrix(1:9,3). See the posting guide, section Examples. (If the surprising behavior does not appear with the sample data, the questioner has to take a deeper look in _his_ data.) But that is what I did after defining the system and labels (like you the documentation): fitols-systemfit(OLS, system, labels) fitsur-systemfit(SUR, system, labels, maxit=100) But after all I think your answers are sufficient. Thanks once again for your support. R and the community are really excellent and a big thread to competitors! [ . . . ] 2) Is there an easy possibility to test a) the OLS equations, and b) the SUR system for SUR structures? In other words: Is the LM-Test from Breusch and Pagan available in R? I don't understand what you want to test. Does the hausman test what you are looking for (see ?hausman.systemfit). If you have questions regarding this test, you might ask my co-author of systemfit, Jeff Hamann. Primarily I want to test if the variance covariance matrix of the OLS residuals is diagonal. But this can be done manually, of course. Please provide the code and a reference to the test. Then, I will add this test to systemfit. This is how R works: useRs become developerR :-) Best wishes, Arne -- Arne Henningsen Department of Agricultural Economics University of Kiel Olshausenstr. 40 D-24098 Kiel (Germany) Tel: +49-431-880 4445 Fax: +49-431-880 1397 [EMAIL PROTECTED] http://www.uni-kiel.de/agrarpol/ahenningsen/ __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] lme in R-2.0.0: Problem with lmeControl
Hello! One note/question hier about specification of control-parameters in the lme(...,control=list(...)) function call: i tried to specify tne number of iteration needed via lme(,control=list(maxIter=..., niterEM=...,msVerbose=TRUE)) but every time i change the defualt values maxIter (e.g. maxIter=1, niterEM=0) on ones specified by me, the call returns all the iterations needed until it's converged. and this is exactly the problem i will to get round. (e.g. in example on p.81 of Pinheiro/Bates,2000: fm1Rail.lme-lme(...,control=list(maxIter=1,...))) so i have tried with option msMaxIter=... and this works. The other problem is, that i even can not see (in R !!!) the output from iterations, despite the msVerbose=TRUE specification and setting options(verbose=TRUE) (The S-plus can do it but also ignoring the maxIter=... specification) Thank you for your hint __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Creating a factor from a combination of vectors
Hi Yves, Using your objects, here is a way: cascombo=do.call(paste,c(cas,sep=.)) factor(do.call(paste,c(df,sep=.)),levels=cascombo,labels=rownames(cas)) [1] LowNA NA NA NA NA NA NA NA NA NA NA Medium NA NA [16] NA NA NA NA NA NA NA NA NA High Levels: Low Medium High It uses: ? paste (sep=.) to create the combinations ie 0.0, 10.50, etc. ? do.call to invoke the paste on the columns of the data.frames ? factor specifying existing levels (only those defined by cas data.frame) anbd labels Eric At 10:12 30/11/2004, Yves Brostaux wrote: Dear list, Here's a little problem I already solved with my own coding style, but I feel there is a more efficient and cleaner way to write it, but had no success finding the clever solution. I want to produce a factor from a subset of the combination of two vectors. I have the vectors a et b in a data-frame : df - expand.grid(a=c(0, 5, 10, 25, 50), b=c(0, 25, 50, 100, 200)) fac.df a b 1 0 0 2 5 0 3 10 0 4 25 0 5 50 0 6 0 25 7 5 25 snip and want to create a factor which levels correspond to particular combinations of a and b (let's say Low for a=0 b=0, Medium for a=10 b=50, High for a=50 b=200, others levels set to NA), reading them from a data-frame which describes the desired subset and corresponding levels. Here's my own solution (inputs are data-frames df and cas, output is the sub factor): cas - as.data.frame(matrix(c(0, 10,50, 0, 50, 200), 3, 2,dimnames=list(c(Low, Medium, High), c(a, b cas a b Low 0 0 Medium 10 50 High 50 200 sub - character(length(df$a)) for (i in 1:length(df$a)) { + temp - rownames(cas)[cas$a==df$a[i] cas$b==df$b[i]] + sub[i] - ifelse(length(temp)0, temp, NA) + } sub - ordered(sub, levels=c(Low, Medium, High)) sub [1] LowNA NA NA NA NA NA NA NA NA NA NA Medium NA NA NA NA [18] NA NA NA NA NA NA NA High Levels: Low Medium High I was looking for a vectorized solution (apply style) binding data-frames df and cas, but didn't succeed avoiding the for loop. Could anybody bring me the ligths over the darkness of my ignorance ? Thank you very much in advance. -- Ir. Yves BROSTAUX Unité de Statistique et Informatique Faculté universitaire des Sciences agronomiques de Gembloux (FUSAGx) 8, avenue de la Faculté B-5030 Gembloux Belgique Tél: +32 81 62 24 69 Email: [EMAIL PROTECTED] __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html Eric Lecoutre UCL / Institut de Statistique Voie du Roman Pays, 20 1348 Louvain-la-Neuve Belgium tel: (+32)(0)10473050 [EMAIL PROTECTED] http://www.stat.ucl.ac.be/ISpersonnel/lecoutre If the statistics are boring, then you've got the wrong numbers. -Edward Tufte __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Creating a factor from a combination of vectors
Yves Brostaux brostaux.y at fsagx.ac.be writes: : : Dear list, : : Here's a little problem I already solved with my own coding style, but I : feel there is a more efficient and cleaner way to write it, but had no : success finding the clever solution. : : I want to produce a factor from a subset of the combination of two : vectors. I have the vectors a et b in a data-frame : : : df - expand.grid(a=c(0, 5, 10, 25, 50), b=c(0, 25, 50, 100, 200)) : fac.df : a b : 1 0 0 : 2 5 0 : 3 10 0 : 4 25 0 : 5 50 0 : 6 0 25 : 7 5 25 : snip : : and want to create a factor which levels correspond to particular : combinations of a and b (let's say Low for a=0 b=0, Medium for a=10 : b=50, High for a=50 b=200, others levels set to NA), reading them from : a data-frame which describes the desired subset and corresponding levels. : : Here's my own solution (inputs are data-frames df and cas, output is the : sub factor): : : cas - as.data.frame(matrix(c(0, 10,50, 0, 50, 200), 3, : 2,dimnames=list(c(Low, Medium, High), c(a, b : cas : a b : Low 0 0 : Medium 10 50 : High 50 200 : : sub - character(length(df$a)) : for (i in 1:length(df$a)) { : + temp - rownames(cas)[cas$a==df$a[i] cas$b==df$b[i]] : + sub[i] - ifelse(length(temp)0, temp, NA) : + } : sub - ordered(sub, levels=c(Low, Medium, High)) : sub : [1] LowNA NA NA NA NA NA NA NA : NA NA NA Medium NA NA NA NA : [18] NA NA NA NA NA NA NA High : Levels: Low Medium High : : I was looking for a vectorized solution (apply style) binding : data-frames df and cas, but didn't succeed avoiding the for loop. Could : anybody bring me the ligths over the darkness of my ignorance ? Thank : you very much in advance. : Use interaction() and factor() like this: factor( interaction(df), lev = c(0.0, 10.50, 50.200), lab = c(Low, Medium, High), ordered = TRUE) __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] A basic question
Hi R users: I want to know any experience compiling R in other LINUX distributions besides FEDORA (Red Hat) or Mandrake, for example in BSD, Debian, Gentoo, Slackware, vector LINUX, Knoppix, Yopper or CERN linux? Hope this is not a basic question Thank you for your help. Kenneth __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] 2k-factorial design with 10 parameters
Hi, I'd like to apply a 2^k factorial design with k=10 parameters. Obviously this results in a quite long term for the model equation due to the high number of combinations of parameters. How can I specify the equation for the linear model (lm) without writing all combinations explicitly down by hand? Does a R command exist for this problematic? Thanks for your help in advance, Sven __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] (sem assunto)
- gora! [[alternative HTML version deleted]] __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Building latest version of package
On Mon, 29 Nov 2004, michael watson (IAH-C) wrote: Hi I have a package which was built using R 1.9.1 and everything worked fine. I recently upgraded to R 2.0.1 and tried to re-install my package - and I got: Error in library(mypackage) : 'mypackage' is not a valid package -- installed 2.0.0? I don't think you re-installed it, rather unzipped the zip file. So I tried rebuilding it using my new version of R: R CMD BUILD --binary mypackage hhc: not found cp: cannot stat `mypackage.chm': No such file or directory make[1]: *** [chm-mypackage] Error 1 make: *** [pkg-mypackage] Error 2 *** Installation of mypackage failed *** Removing 'f:/tmp/Rbuild.2972/mypackage' ERROR * installation failed I didn't have these problems before. What is hhc and why can't R find it? README.packages says what it is, and R is not looking for it, but make is. Probably because you didn't check the checklist in README.packages. This is not a new requirement. In general, will I have to re-build my package everytime a new version of R is released? No. But we are talking about installing, not building, here. Please look in `Writing R Extensions' to see the difference. -- Brian D. Ripley, [EMAIL PROTECTED] Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/ University of Oxford, Tel: +44 1865 272861 (self) 1 South Parks Road, +44 1865 272866 (PA) Oxford OX1 3TG, UKFax: +44 1865 272595 __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] plotting data in non-orthogonal coords.
On 30 Nov 2004 at 11:06, Andreas Franke wrote: snip Hi ! Thanks for replying to my post and sorry for not being specific enough. Maybe I am the one who didnt get the point , but as far as I understand R plots filled.contour(x,y,z,...) in the following way: x,y define a grid in cartesian coords, i.e. the angle between x and y is 90. So if I have data on such a grid I am fine. My data is on an equally spaced grid in a coordsystem where x and y are at an angle of 60. If you transform into cartesiancoords this isnt an equally spaced grid anymore. You could interpret it as an equally spaced grid on which there is only data given on every second grid point. It would be nice if one could just plot data given as F(x,y) where you supply x and y for every data point seperatly so that you dont need any specific grid. Maybe interp() in akima package can help you, but as I said it strongly depends on what you really want to achieve. Cheers Petr I hope that someone can help. Thanks in advance. Andreas Petr Pikal [EMAIL PROTECTED] __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] 2k-factorial design with 10 parameters
Hi Sven, just use: lm(y~(x1+x2+x3+...+x10)^10) e.g., y - rnorm(5000) x1 - factor(sample(0:1, 5000, TRUE)) x2 - factor(sample(0:1, 5000, TRUE)) x3 - factor(sample(0:1, 5000, TRUE)) x4 - factor(sample(0:1, 5000, TRUE)) lm1 - lm(y~(x1+x2+x3+x4)^4) summary(lm1) I hope it helps. Best, Dimitris Dimitris Rizopoulos Ph.D. Student Biostatistical Centre School of Public Health Catholic University of Leuven Address: Kapucijnenvoer 35, Leuven, Belgium Tel: +32/16/336899 Fax: +32/16/337015 Web: http://www.med.kuleuven.ac.be/biostat http://www.student.kuleuven.ac.be/~m0390867/dimitris.htm - Original Message - From: Sven [EMAIL PROTECTED] To: [EMAIL PROTECTED] Sent: Tuesday, November 30, 2004 12:59 PM Subject: [R] 2k-factorial design with 10 parameters Hi, I'd like to apply a 2^k factorial design with k=10 parameters. Obviously this results in a quite long term for the model equation due to the high number of combinations of parameters. How can I specify the equation for the linear model (lm) without writing all combinations explicitly down by hand? Does a R command exist for this problematic? Thanks for your help in advance, Sven __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] 2k-factorial design with 10 parameters
On Tue, 30 Nov 2004, Sven wrote: I'd like to apply a 2^k factorial design with k=10 parameters. Obviously this results in a quite long term for the model equation due to the high number of combinations of parameters. How can I specify the equation for the linear model (lm) without writing all combinations explicitly down by hand? Does a R command exist for this problematic? I assume you mean k=10 factors (there are a lot more parameters). aov(y ~ .^10, data=mydata) will do what you are probably asking, if you have a data frame with response y and the ten factors. I'm not sure how you could analyse the 1000 odd lines of output, so reduce 10 to something sensible (like 2 or 3) -- Brian D. Ripley, [EMAIL PROTECTED] Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/ University of Oxford, Tel: +44 1865 272861 (self) 1 South Parks Road, +44 1865 272866 (PA) Oxford OX1 3TG, UKFax: +44 1865 272595 __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Newsletter - Live-Jackpot und taegliches Glueckshoroskop auf www.casinos.ch
Live-Jackpot und tägliches Glückshoroskop auf www.casinos.ch Seit dieser Woche stellt die Nr. 1 Casino-Plattform der Schweiz seinen Besuchern zwei weitere, exklusive Dienstleistungen zur Verfügung. DIE LIVE-JACKPOT-ANBINDUNG Nichts ist ärgerlicher für Kunden, als veraltete oder verspätete Informationen. Darum bietet casinos.ch den wohl aktuellsten Schweizer Jackpot-Service im Internet! Aufgrund der guten Zusammenarbeit mit unseren Partnern und modernster IT sind wir in der Lage die Jackpot-Stände von mehreren Schweizer Casinos Live anzubieten. Zur Zeit sind der Swiss Jackpot sowie die Jackpots der Casinos von Zürichsee, St.Gallen, Schaffhausen und Bad Ragaz angeschlossen. In Kürze werden weitere Jackpots von Schweizer Casinos angeschlossen werden. Nirgendwo sonst finden Sie eine aktuellere Übersicht über die Schweizer Casino-Jackpots. Link zur Jackpot-Uebersicht http://www.megajackpot.ch DAS TAEGLICHE GLUECKSHOROSKOP Es beantwortet jeden Tag die Frage, ob die Sterne für das Glücksspiel günstig stehen. Welche Symbole sind heute der Jungfrau hold, oder auf was sollen Zwillinge beim Kartenspiel besonders achten? Mit einem Klick wissen Sie es. Für besondere Tage können Sie sich bei unserem Partner www.astro-service.ch auch ein ganz persönliches Glückshoroskop erstellen lassen. Link zum täglichen Glückshoroskop http://www.glueckshoroskop.ch Nebst diesen beiden exklusiven Neuerungen finden Casino-Interessierte, -Betreiber, -Angestellte, Newcomers u.a. auch weiterhin alles Wissenswerte über Casinos und Glücksspiele 2-sprachig auf www.casinos.ch - Tägliche News (bereits über 1000 News im 2004) - Über 2400 Casino-Adressen und Detail-Informationen - Fotogalerien und Interviews - Turnier und Eventkalender - Spielerklärungen zu allen Casino-Spielen - Gesetze, Facts Figures und vieles mehr Good Luck wünscht Ihr Newsletter Team Casinos.ch Wir bitten um Entschuldigung, falls Sie diese Informationen unerwuenscht erhalten.. Sie erhalten diesen Casinos-Informations-Newsletter augrund Ihres Eintrages auf www.casinos.ch, www.help.ch oder einer unserer Partner-Plattformen. Sollten Sie KEINEN NEWSLETTER mehr wünschen, so klicken Sie bitte auf folgenden Link. http://www.casinos.ch/unsubscribe.cfm (c) 1996-2004 www.casinos.ch und www.help.ch [[alternative HTML version deleted]] __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] How to know if a bug was recognised
Hello! A problem with special characters seemed to me to be a bug. I sent a mail to [EMAIL PROTECTED] concerning the problem (see below). How can I find out, if this is considered as a bug or an error of myself? Which part of FAQs or documentation did I miss to find the answer? thanks in advance Heinz Tüchler copy of abovementioned mail -- to: [EMAIL PROTECTED] subject: problem with special characters (ä,ö,ü) Dear Developers! Using special characters I found a strange behaviour in R 2.0.1 and equally in R : Copyright 2004, The R Foundation for Statistical Computing Version 2.0.1 (2004-11-15), ISBN 3-900051-07-0 Operating System: Windows 98SE example: factor1-as.factor(c(weiblich,männlich,österreichisch,frühreif,Gruß )) factor1 factor1 [1] weiblich m\344nnlich\366sterreichisch fr\374hreif [5] Gru\337 Levels: frühreif Gruß männlich österreichisch weiblich with best wishes Heinz Tüchler __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] 2k-factorial design with 10 parameters
On 30 Nov 2004 at 12:59, Sven wrote: Hi, I'd like to apply a 2^k factorial design with k=10 parameters. Obviously this results in a quite long term for the model equation due to the high number of combinations of parameters. How can I specify the equation for the linear model (lm) without writing all combinations explicitly down by hand? Does a R command exist for this problematic? Hi Sven from ?lm The specification 'first*second' indicates the _cross_ of 'first' and 'second'. This is the same as 'first + second + first:second' and from ?formula ## Create a formula for a model with a large number of variables: xnam - paste(x, 1:25, sep=) (fmla - as.formula(paste(y ~ , paste(xnam, collapse= + If you change 1:25 to 1:10 and collapse to * and use fmla in your model you will get what you want (I suppose). But I woder if it has any sense. Cheers Petr Thanks for your help in advance, Sven __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html Petr Pikal [EMAIL PROTECTED] __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] How to know if a bug was recognised
You have already been sent an answer. It is a bug in your copy of Windows, and it will be worked around in the current version of R-patched. From the CHANGES file: R 2.0.1 patched === We work around reported bugs in Windows XP as to which characters are printable by attempting to print all non-control characters when using print(). Note: no one else has reported a problem on 98SE, despite this having been the behaviour of R for three months, and it seemed only XP SP2 was affected. Indeed, no one reported the problem for 2.0.0 at all, including all the alpha and beta test versions (except for Chinese where the characters are invalid and so the behaviour was correct), and so the workaround did not make 2.0.1. BTW, your expectation that an email you sent at the weekend will be answered by Tuesday is completely unreasonable. R is a volunteer project, and the developers do have other commitments (and occasionally make attempts to have a life). [You could have read the archives of the R mailing lists to find that this was a known issue that had already been addressed.] On Tue, 30 Nov 2004, Heinz Tuechler wrote: Hello! A problem with special characters seemed to me to be a bug. I sent a mail to [EMAIL PROTECTED] concerning the problem (see below). How can I find out, if this is considered as a bug or an error of myself? Which part of FAQs or documentation did I miss to find the answer? thanks in advance Heinz Tüchler copy of abovementioned mail -- to: [EMAIL PROTECTED] subject: problem with special characters (ä,ö,ü) Dear Developers! Using special characters I found a strange behaviour in R 2.0.1 and equally in R : Copyright 2004, The R Foundation for Statistical Computing Version 2.0.1 (2004-11-15), ISBN 3-900051-07-0 Operating System: Windows 98SE example: factor1-as.factor(c(weiblich,männlich,österreichisch,frühreif,Gruß )) factor1 factor1 [1] weiblich m\344nnlich\366sterreichisch fr\374hreif [5] Gru\337 Levels: frühreif Gruß männlich österreichisch weiblich with best wishes Heinz Tüchler __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html -- Brian D. Ripley, [EMAIL PROTECTED] Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/ University of Oxford, Tel: +44 1865 272861 (self) 1 South Parks Road, +44 1865 272866 (PA) Oxford OX1 3TG, UKFax: +44 1865 272595__ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
RE: [R] How to know if a bug was recognised
-Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Heinz Tuechler Sent: Tuesday, November 30, 2004 1:25 PM To: [EMAIL PROTECTED] Subject: [R] How to know if a bug was recognised Hello! A problem with special characters seemed to me to be a bug. I sent a mail to [EMAIL PROTECTED] concerning the problem (see below). How can I find out, if this is considered as a bug or an error of myself? Which part of FAQs or documentation did I miss to find the answer? This will not answer your question on what is a bug or not, but if you don't know, the R team has kindly made a fix for this problem. What I remember from an earlier thread, this was not really due to R, but to Windows. For the latest R v2.0.1 patch it now seems to work as before/expected: R : Copyright 2004, The R Foundation for Statistical Computing Version 2.0.1 Patched (2004-11-27), ISBN 3-900051-07-0 å [1] å ä [1] ä ö [1] ö Cheers Henrik Bengtsson thanks in advance Heinz Tüchler copy of abovementioned mail -- to: [EMAIL PROTECTED] subject: problem with special characters (ä,ö,ü) Dear Developers! Using special characters I found a strange behaviour in R 2.0.1 and equally in R : Copyright 2004, The R Foundation for Statistical Computing Version 2.0.1 (2004-11-15), ISBN 3-900051-07-0 Operating System: Windows 98SE example: factor1-as.factor(c(weiblich,männlich,österreichisch,f rühreif,Gruß )) factor1 factor1 [1] weiblich m\344nnlich\366sterreichisch fr\374hreif [5] Gru\337 Levels: frühreif Gruß männlich österreichisch weiblich with best wishes Heinz Tüchler __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Opening connection to FTP site
Hi Is it possible to open a connection to an FTP site such that I can read the directory listing? Eg: URL - url(ftp://ftp.ensembl.org;, open=r) Error in url(ftp://ftp.ensembl.org;, open=r) : unable to open connection URL - url(ftp://ftp.ensembl.org;) open(URL) Error in open.connection(URL) : unable to open connection I think perhaps it is because there isn't actually a file there to connect to, eg this works fine: URL - url(ftp://ftp.ensembl.org/pub/README;, open=r) Thanks in advance Mick __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Opening connection to FTP site
On Tue, 30 Nov 2004, michael watson (IAH-C) wrote: Hi Is it possible to open a connection to an FTP site such that I can read the directory listing? Eg: URL - url(ftp://ftp.ensembl.org;, open=r) Error in url(ftp://ftp.ensembl.org;, open=r) : unable to open connection URL - url(ftp://ftp.ensembl.org;) open(URL) Error in open.connection(URL) : unable to open connection I think perhaps it is because there isn't actually a file there to connect to, eg this works fine: URL - url(ftp://ftp.ensembl.org/pub/README;, open=r) It is not possible using url(). Try, e.g. tmp - tempfile() download.file(ftp://ftp.ensembl.org;, tmp, method=lynx) # or wget readLines(tmp) -- Brian D. Ripley, [EMAIL PROTECTED] Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/ University of Oxford, Tel: +44 1865 272861 (self) 1 South Parks Road, +44 1865 272866 (PA) Oxford OX1 3TG, UKFax: +44 1865 272595 __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] lme in R-2.0.0: Problem with lmeControl
Pavel Khomski wrote: Hello! One note/question hier about specification of control-parameters in the lme(...,control=list(...)) function call: i tried to specify tne number of iteration needed via lme(,control=list(maxIter=..., niterEM=...,msVerbose=TRUE)) but every time i change the defualt values maxIter (e.g. maxIter=1, niterEM=0) on ones specified by me, the call returns all the iterations needed until it's converged. and this is exactly the problem i will to get round. (e.g. in example on p.81 of Pinheiro/Bates,2000: fm1Rail.lme-lme(...,control=list(maxIter=1,...))) so i have tried with option msMaxIter=... and this works. The other problem is, that i even can not see (in R !!!) the output from iterations, despite the msVerbose=TRUE specification and setting options(verbose=TRUE) (The S-plus can do it but also ignoring the maxIter=... specification) Thank you for your hint __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html One difference between the S-PLUS and the R versions of lme is the optimizer that is used. In S-PLUS the ms() function is used to optimize the log-likelihood. In R the most reasonable choices are optim or nlm. The version of lme in the current nlme package uses optim, which has a more sophisticated verbose option than just an on/off switch. It has several levels of verbosity. If we say that msVerbose corresponds to the lowest non-silent level then it only prints out intermediate results every five iterations and that example converges before 5 iterations. library(nlme) fm1Rail.lme - lme(travel ~ 1, Rail, ~ 1|Rail, +control=list(niterEM=0,msVerbose=TRUE)) initial value 67.893737 final value 61.048859 converged If we were to set msVerbose=TRUE to give the highest level of verbosity you would be innundated with output. The version of lme in the current lme4 package allows the optimizer to be chosen. (The lme4 package cannot be loaded in the same session with the nlme package. You must quit R and restart to be able to load the lme4 package). library(lme4) Loading required package: Matrix Loading required package: latticeExtra fm1Rail.lme - lme(travel ~ 1, Rail, ~ 1 | Rail, + control = list(msVerbose = TRUE, optimizer = nlm, niterEM = 0)) iteration = 0 Step: [1] 0 Parameter: [1] 0.1177830 Function Value [1] 143.9911 Gradient: [1] 7.849722 iteration = 1 Step: [1] -7.849722 Parameter: [1] -7.731939 Function Value [1] 136.7956 Gradient: [1] -4.880857 iteration = 2 Step: [1] 3.009554 Parameter: [1] -4.722385 Function Value [1] 123.8982 Gradient: [1] -2.879458 iteration = 3 Step: [1] 0.9505343 Parameter: [1] -3.771850 Function Value [1] 122.207 Gradient: [1] -0.4481287 iteration = 4 Step: [1] 0.1751970 Parameter: [1] -3.596653 Function Value [1] 122.1802 Gradient: [1] 0.1486718 iteration = 5 Step: [1] -0.04364416 Parameter: [1] -3.640298 Function Value [1] 122.177 Gradient: [1] -0.003887335 iteration = 6 Step: [1] 0.00111209 Parameter: [1] -3.639185 Function Value [1] 122.177 Gradient: [1] -3.100244e-05 iteration = 7 Parameter: [1] -3.639177 Function Value [1] 122.177 Gradient: [1] 6.643475e-09 Relative gradient close to zero. Current iterate is probably solution. Those results do not match the output in our book because the version in lme4 uses the deviance as the objective function. (One of the difficulties of writing a book about a particular piece of software is that the software is likely to change much more rapidly than the book.) I show this with some trepidation because I am in the process of changing the optimization within lme yet again. The development version ignores optimizer = 'nlm' because it phrases the problem as a constrained optimization problem and uses optim unconditionally. The full level of verbosity of optim, which I occasionally use for development purposes, is very verbose fm1Rail.lme - lme1(travel ~ 1, Rail, ~ 1 | Rail, + control = list(msVerbose = TRUE, optimizer = nlm, niterEM = 0)) N = 1, M = 5 machine precision = 2.22045e-16 L = 1e-10 X0 = 0.89 U = inf At X0, 0 variables are exactly at the bounds At iterate 0 f= 143.99 |proj g|= 8.8309 Iteration 0 CAUCHY entered--- There are 0 breakpoints GCP found in this segment Piece 1 f1, f2 at start point -7.7985e+01 7.7985e+01 Distance to the stationary point = 1.e+00 Cauchy X = 9.71983 exit CAUCHY-- 1 variables are free at GCP on iteration 1 LINE SEARCH 0 times; norm of step = 1 X = 1.9 G = -4.46694 Iteration 1 CAUCHY entered--- There are 0 breakpoints GCP found in this segment Piece 1 f1, f2 at start point -1.9954e+01 8.7077e+01 Distance to the stationary point = 2.2915e-01 Cauchy X = 2.91248 exit
[R] Info
I am having difficulty obtaining the scores from my principal component analysis. I have used this method before and have had no problems. The data set that I am using this time is similar to what I have used in the past. What do I need to do to my dataset in order for me to obtain these scores? R screen says the following message Error in factanal(covmat = pasa.cov, factors = 4) : Unable to optimize from these starting value(s) many thanks Catherine KSS Ltd Seventh Floor St James's Buildings 79 Oxford Street Manchester M1 6SS England Company Registration Number 2800886 Tel: +44 (0) 161 228 0040 Fax: +44 (0) 161 236 6305 mailto:[EMAIL PROTECTED]http://www.kssg.com The information in this Internet email is confidential and m...{{dropped}} __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] A basic question
Kenneth wrote: I want to know any experience compiling R in other LINUX distributions besides FEDORA (Red Hat) or Mandrake, for example in BSD, Debian, Gentoo, Slackware, vector LINUX, Knoppix, Yopper or CERN linux? Hope this is not a basic question Thank you for your help. There is considerable experience compiling R under Debian Linux. Many of the developers use Debian and if you check the sources you will find that there is a debian directory in the official source distribution. The daily package checking is done on a system running Debian and there are dozens of R packages in the Debian distribution. See http://packages.qa.debian.org/r/r-base-core for a history of the uploads. The link to the buildd logs shows compilation of R under Debian on many different architectures. Because Knoppix is derived from Debian and uses the Debian packaging system the compilation of R under Knoppix is essentially the same as under Debian. The Quantian distribution comes with R installed. __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] A basic question
Kenneth [EMAIL PROTECTED] writes: Hi R users: I want to know any experience compiling R in other LINUX distributions besides FEDORA (Red Hat) or Mandrake, for example in BSD, Debian, Gentoo, Slackware, vector LINUX, Knoppix, Yopper or CERN linux? Hope this is not a basic question BSD is not Linux... I'm fairly sure we have people checking BSD (perhaps even on the core team. Ross?), and also SuSE and Gentoo. We definitely have core members using Debian, and Knoppix is just a Debian variant (see also Quantian). CERN Linux is a RedHat variant. Don't know about Yoper, Slackware, and vector Linux (a Slackware derivative), but building frome source is not generally a problem on Linux. -- O__ Peter Dalgaard Blegdamsvej 3 c/ /'_ --- Dept. of Biostatistics 2200 Cph. N (*) \(*) -- University of Copenhagen Denmark Ph: (+45) 35327918 ~~ - ([EMAIL PROTECTED]) FAX: (+45) 35327907 __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
RE: [R] Info
It looks like factanal is unable to optimize from these starting values (kinda like the error message says). So, factanal.fit.mle isn't converging and you have problems with your analysis. Try putting control = list(trace = T) in your code to see what happenens. E.g., R R v1 - c(1,1,1,1,1,1,1,1,1,1,3,3,3,3,3,4,5,6) R v2 - c(1,2,1,1,1,1,2,1,2,1,3,4,3,3,3,4,6,5) R v3 - c(3,3,3,3,3,1,1,1,1,1,1,1,1,1,1,5,4,6) R v4 - c(3,3,4,3,3,1,1,2,1,1,1,1,2,1,1,5,6,4) R v5 - c(1,1,1,1,1,3,3,3,3,3,1,1,1,1,1,6,4,5) R v6 - c(1,1,1,2,1,3,3,3,4,3,1,1,1,2,1,6,5,4) R m1 - cbind(v1,v2,v3,v4,v5,v6) R factanal(m1, factors=3, control = list(trace = T)) start 1 value: 0.4755156 uniqs: 0.0050 0.1009 0.0050 0.2241 0.0843 0.0050 Call: factanal(x = m1, factors = 3, control = list(trace = T)) Uniquenesses: v1v2v3v4v5v6 0.005 0.101 0.005 0.224 0.084 0.005 Loadings: Factor1 Factor2 Factor3 v1 0.944 0.182 0.267 v2 0.905 0.235 0.159 v3 0.236 0.210 0.946 v4 0.180 0.242 0.828 v5 0.242 0.881 0.286 v6 0.193 0.959 0.196 Factor1 Factor2 Factor3 SS loadings 1.893 1.886 1.797 Proportion Var 0.316 0.314 0.300 Cumulative Var 0.316 0.630 0.929 The degrees of freedom for the model is 0 and the fit was 0.4755 R If you think the model should be OK and there isn't an error somewhere else then you'll want to fiddle with the control options. From the help for fractanal: control: A list of control values, nstart The number of starting values to be tried if 'start = NULL'. Default 1. trace logical. Output tracing information? Default 'FALSE'. lower The lower bound for uniquenesses during optimization. Should be 0. Default 0.005. opt A list of control values to be passed to 'optim''s 'control' argument. rotate a list of additional arguments for the rotation function. ...: Components of 'control' can also be supplied as named arguments to 'factanal'. HTH, Andy -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] Behalf Of Catherine Dempsey Sent: Tuesday, November 30, 2004 7:31 AM To: '[EMAIL PROTECTED]' Subject: [R] Info I am having difficulty obtaining the scores from my principal component analysis. I have used this method before and have had no problems. The data set that I am using this time is similar to what I have used in the past. What do I need to do to my dataset in order for me to obtain these scores? R screen says the following message Error in factanal(covmat = pasa.cov, factors = 4) : Unable to optimize from these starting value(s) many thanks Catherine KSS Ltd Seventh Floor St James's Buildings 79 Oxford Street Manchester M1 6SS England Company Registration Number 2800886 Tel: +44 (0) 161 228 0040 Fax: +44 (0) 161 236 6305 mailto:[EMAIL PROTECTED] http://www.kssg.com The information in this Internet email is confidential and m...{{dropped}} __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] A basic question
On Tue, 2004-11-30 at 13:58, Kenneth wrote: Hi R users: I want to know any experience compiling R in other LINUX distributions besides FEDORA (Red Hat) or Mandrake, for example in BSD, Debian, Gentoo, Slackware, vector LINUX, Knoppix, Yopper or CERN linux? Hope this is not a basic question Thank you for your help. I assume that the following will typically work: Get the source file, gunzip and untar, cd to the created directory and type: ./configure make sudo make install It is best to check the resulting configuration after ./configure and get the software (compilers, libraries, packages, utilities) you need for the missing functionality you want to have. It is also wise to run 'make check' after 'make' so that you see if you can trust your compilation. This make check fails in some cases: at least standard package 'foreign' failed 'make check' in ppc architecture both in Red Hat/Fedora based (Yellowdog) and Debian based (Ubuntu) Linuxes when I tried last time. Otherwise the compilation seems to run smoothly (and you may not need 'foreign'). BSD is not Linux, but R is officially supported at least for one version of BSD with GNU tools: MacOS X. cheers,jari oksanen -- Jari Oksanen [EMAIL PROTECTED] __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Testing for S4 objects
Let me suggest a different test, because slotNames was written to work differently when given a string or a class definition. With your definition, R x - classRepresentation R isS4object(x) [1] TRUE which I assume is not what you wanted. (Given a single string, slotNames() tries to look up the class definition of that name.) How about the following? The logic is that an S4 object must have an actual class attribute of length 1 (that rules out basic data types, where class(x) is a string but there is no actual attribute, and also rules out some S3 objects). Then if that's true, try to look up the class definition. If it is non-null, seems like an S4 object. R isS4object - function(object)(length(attr(object, class))==1 + !is.null(getClass(class(object R isS4object(x) [1] FALSE R isS4object(getClass(class(x))) [1] TRUE This definition seems to work, at least on the examples I could think of right away. Notice though, that some classes, such as ts, that have been around for a long while are nevertheless legitimate S4 classes, so: R t1 = ts(1:12) R isS4object(t1) [1] TRUE (this applies to either version of isS4object). There are a couple of details, more appropriate for the r-devel list. Seems a good candidate for a function to add to R. On Sat, 27 Nov 2004 17:48:30 -0500, John Fox [EMAIL PROTECTED] wrote: Dear Martin, As it turns out, the test that I proposed (i.e., testing for NULL slotNames) sometimes fails. For example: library(car) data(Prestige) sum - summary(lm(prestige ~ income + education, data=Prestige)) slotNames(sum) character(0) The following, however, seems to work (at least as far as I've been able to ascertain): isS4object - function(object) length(slotNames(object)) != 0 I hope that this is a more robust test. John John Fox Department of Sociology McMaster University Hamilton, Ontario Canada L8S 4M4 905-525-9140x23604 http://socserv.mcmaster.ca/jfox -Original Message- From: Martin Maechler [mailto:[EMAIL PROTECTED] Sent: Friday, November 26, 2004 3:18 AM To: John Fox Cc: [EMAIL PROTECTED] Subject: Re: [R] Testing for S4 objects JohnF == John Fox [EMAIL PROTECTED] on Thu, 25 Nov 2004 22:28:50 -0500 writes: JohnF Dear r-help list members, Is there a way to test JohnF whether an object is an S4 object? The best that I've JohnF been able to come up with is JohnFisS4object - function(object) !(is.null(slotNames(object))) you can drop one pair of (..) to give isS4object - function(object) !is.null(slotNames(object)) JohnF which assumes that an S4 object has at least one JohnF slot. I think this is safe, but perhaps I'm missing JohnF something. The question is a very good one -- that I have posed to R-core a while ago myself. Inside utils:::str.default {which doesn't show the many commments in the *source* of str.default()}, I have wanted a way that even works when the 'methods' package is not attached and use the more obscure #NOT yet:if(has.class - !is.null(cl - class(object))) if(has.class - !is.null(cl - attr(object, class)))# S3 or S4 class S4 - !is.null(attr(cl, package))## 'kludge' FIXME! ##or length(methods::getSlots(cl)) 0 For the time being, I'd keep your function, but I don't think we'd guarantee that it will remain the appropriate test in all future. But till then many things will have happened (if not all of them ;-). Martin Maechler, ETH Zurich __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] glmmPQL
Dear listmembers, I've adjusted a mixed model with glmmPQL: nulo-glmmPQL(POS~1,random=~1|GRUPO, family=binomial, data=new) and I've reched the following results: Linear mixed-effects model fit by maximum likelihood Data: new AIC BIClogLik 53238.5 53260.74 -26616.25 Random effects: Formula: ~1 | GRUPO (Intercept) Residual StdDev: 0.3402137 0.9952645 Variance function: Structure: fixed weights Formula: ~invwt Fixed effects: POS ~ 1 Value Std.ErrorDF t-value p-value (Intercept) 0.6214472 0.03723763 12025 16.68869 0 Standardized Within-Group Residuals: Min Q1Med Q3Max -1.7831032 -1.2642113 0.6508504 0.7058691 1.1945426 Number of Observations: 12227 Number of Groups: 202 Could someone clarify me? I don't understand why DF=12025 in the intercept t-test above, if the objective is to estimate only one mean for all groups (mean=0,6214472). I expected that this DF would equal 201, as I have 202 groups. Thanks in advance, Alex __ Acabe com aquelas janelinhas que pulam na sua tela. AntiPop-up UOL - É grátis! http://antipopup.uol.com.br/ __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Attn Heinz Tuechler: Re: problem with special characters (ä,ö,ü)
[I tried to send this message privately, but the return address bounced.] I think this has been fixed in R-patched, but I doubt if the fix has been tested in Win98. Could you please download a copy from http://cran.r-project.org/bin/windows/base/rpatched.html and confirm that it has been fixed? Duncan Murdoch On Sat, 27 Nov 2004 23:31:23 +0100, Heinz Tuechler [EMAIL PROTECTED] wrote : Dear Developers! Using special characters I found a strange behaviour in R 2.0.1 and equally in R : Copyright 2004, The R Foundation for Statistical Computing Version 2.0.1 (2004-11-15), ISBN 3-900051-07-0 Operating System: Windows 98SE example: factor1-as.factor(c(weiblich,männlich,österreichisch,frühreif,Gruß )) factor1 factor1 [1] weiblich m\344nnlich\366sterreichisch fr\374hreif [5] Gru\337 Levels: frühreif Gruß männlich österreichisch weiblich with best wishes Heinz Tüchler __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
RE: [R] Info
Also, factanal() does not do `principal component analysis', and it may well be that the data are inappropriate for factor analysis if they are appropriate for PCA. If PCA was really intended, prcomp() and princomp() are appropriate tools. On Tue, 30 Nov 2004, Andy Bunn wrote: It looks like factanal is unable to optimize from these starting values (kinda like the error message says). So, factanal.fit.mle isn't converging and you have problems with your analysis. Try putting control = list(trace = T) in your code to see what happenens. E.g., R R v1 - c(1,1,1,1,1,1,1,1,1,1,3,3,3,3,3,4,5,6) R v2 - c(1,2,1,1,1,1,2,1,2,1,3,4,3,3,3,4,6,5) R v3 - c(3,3,3,3,3,1,1,1,1,1,1,1,1,1,1,5,4,6) R v4 - c(3,3,4,3,3,1,1,2,1,1,1,1,2,1,1,5,6,4) R v5 - c(1,1,1,1,1,3,3,3,3,3,1,1,1,1,1,6,4,5) R v6 - c(1,1,1,2,1,3,3,3,4,3,1,1,1,2,1,6,5,4) R m1 - cbind(v1,v2,v3,v4,v5,v6) R factanal(m1, factors=3, control = list(trace = T)) start 1 value: 0.4755156 uniqs: 0.0050 0.1009 0.0050 0.2241 0.0843 0.0050 Call: factanal(x = m1, factors = 3, control = list(trace = T)) Uniquenesses: v1v2v3v4v5v6 0.005 0.101 0.005 0.224 0.084 0.005 Loadings: Factor1 Factor2 Factor3 v1 0.944 0.182 0.267 v2 0.905 0.235 0.159 v3 0.236 0.210 0.946 v4 0.180 0.242 0.828 v5 0.242 0.881 0.286 v6 0.193 0.959 0.196 Factor1 Factor2 Factor3 SS loadings 1.893 1.886 1.797 Proportion Var 0.316 0.314 0.300 Cumulative Var 0.316 0.630 0.929 The degrees of freedom for the model is 0 and the fit was 0.4755 R If you think the model should be OK and there isn't an error somewhere else then you'll want to fiddle with the control options. From the help for fractanal: control: A list of control values, nstart The number of starting values to be tried if 'start = NULL'. Default 1. trace logical. Output tracing information? Default 'FALSE'. lower The lower bound for uniquenesses during optimization. Should be 0. Default 0.005. opt A list of control values to be passed to 'optim''s 'control' argument. rotate a list of additional arguments for the rotation function. ...: Components of 'control' can also be supplied as named arguments to 'factanal'. HTH, Andy -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] Behalf Of Catherine Dempsey Sent: Tuesday, November 30, 2004 7:31 AM To: '[EMAIL PROTECTED]' Subject: [R] Info I am having difficulty obtaining the scores from my principal component analysis. I have used this method before and have had no problems. The data set that I am using this time is similar to what I have used in the past. What do I need to do to my dataset in order for me to obtain these scores? R screen says the following message Error in factanal(covmat = pasa.cov, factors = 4) : Unable to optimize from these starting value(s) many thanks Catherine KSS Ltd Seventh Floor St James's Buildings 79 Oxford Street Manchester M1 6SS England Company Registration Number 2800886 Tel: +44 (0) 161 228 0040 Fax: +44 (0) 161 236 6305 mailto:[EMAIL PROTECTED]http://www.kssg.com The information in this Internet email is confidential and m...{{dropped}} __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html -- Brian D. Ripley, [EMAIL PROTECTED] Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/ University of Oxford, Tel: +44 1865 272861 (self) 1 South Parks Road, +44 1865 272866 (PA) Oxford OX1 3TG, UKFax: +44 1865 272595 __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] plotting data in non-orthogonal coords.
On Tuesday 30 November 2004 04:06, Andreas Franke wrote: [...] It would be nice if one could just plot data given as F(x,y) where you supply x and y for every data point seperatly so that you dont need any specific grid. This is one solution, but it's not exactly what you want: library(lattice) u - row(matrix(0, nrow = 10, ncol = 15)) v - col(matrix(0, nrow = 10, ncol = 15)) x - u y - .5 * u + .3 * v z - log(u + v) wireframe(z ~ x * y) Deepayan __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] How to know if a bug was recognised
On Tue, 30 Nov 2004 13:24:43 +0100, Heinz Tuechler [EMAIL PROTECTED] wrote : Hello! A problem with special characters seemed to me to be a bug. I sent a mail to [EMAIL PROTECTED] concerning the problem (see below). How can I find out, if this is considered as a bug or an error of myself? Which part of FAQs or documentation did I miss to find the answer? If you send a private email, please use a return address that works. I got messages that [EMAIL PROTECTED] has been disabled when I tried to respond there. Duncan Murdoch __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Package for multivariate binary logistic regression?
I am trying to find out if someone has implemented a (McFadden-type) multivariate binary logistic regresssion package for R? From what I can tell, this is not available for R. Thank you, Lynne Baker [[alternative HTML version deleted]] __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] (no subject)
Hello, I am trying to estimate a choice model with varying choice set for each individual. I would like to fit different kinds of model (logit ,nested logit, probit...). So far I have found that package *mnp* allows me to estimate a probit model with varying choice set. But for estimation of a logit model, I have only found function *multinom* of package *nnet* which does not seem to allow for varying choice set. I could incorporate indicators of choice availability as explanotary variables, but it does not seem a very good way to do it. Instead, for a logit model, I have coded a likelihood computation of the underlying model with varying choice set and I use optim function to get the maximum. I wondered if there were more user friendly functions available and/or other choice model related package. Thanks, Julien __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] adding regression curve to xyplot
Dear R-listers, It seems that predict() behaves differently within panel.xyplot. Am I doing something stupid? Thanks, Carlisle First, without xyplot(): lmtest - lm(t~s,data=subset(P100,whichLon100==1 whichLat100==1)) lmtest Call: lm(formula = s ~ t, data = subset(P100, whichLon100 == 1 whichLat100 == 1)) Coefficients: (Intercept)t 33.3307 0.1393 range(P100$t) [1] 4.050469 24.514543 predict(lmtest,newdata=data.frame(t=range(P100$t))) 12 33.89501 36.74620 As expected, predict gives two values. But inside xyplot() predict gives 300 values: xyplot(t~s|factor(lonLabels[whichLon100])*factor(latLabels[whichLat100]), + data=P100,pch=., + panel=function(x,y,...){panel.xyplot(x,y,...) + thislm - lm(x~y) + print(thislm) + newt - range(P100$t) + print(newt) + news - as.vector(predict(thislm,newdata=data.frame(t=newt))) + print(news) + llines(news,newt,col=red)}) Call: lm(formula = x ~ y) Coefficients: (Intercept)y 33.3307 0.1393 [1] 4.050469 24.514543 [1] 34.16173 35.31284 34.95317 35.62314 34.64448 34.06225 34.19688 34.03391 [9] 33.90860 35.28849 35.29911 34.61618 35.19837 35.28966 34.91978 35.32388 [17] 35.39351 35.54533 35.58760 34.77039 35.07226 35.35643 35.40594 33.98609 [25] 33.96461 33.91158 34.12389 34.33804 34.72235 34.63541 36.20420 36.13635 [33] 34.60623 34.32401 35.59768 34.68576 34.64661 34.58804 34.74548 35.09062 [41] 34.70290 34.22428 35.12743 34.90726 34.52325 34.90041 35.46984 34.79572 [49] 35.47026 35.35481 34.70722 34.08883 33.97586 33.94797 33.96165 33.97715 [57] 33.94886 33.99715 34.10887 34.72597 34.20534 34.45016 35.00769 34.56742 [65] 34.76119 34.87190 34.60760 34.50113 34.56594 34.65954 34.57076 34.91072 [73] 34.97322 34.99036 34.48229 34.58436 34.56767 34.94204 34.95929 34.89107 [81] 34.98846 34.51328 34.74252 34.61337 34.62212 34.70953 34.74080 34.71630 [89] 34.68599 35.58629 34.77031 34.49366 34.49873 34.48112 35.11327 34.62598 [97] 34.50436 34.50705 34.70170 35.01278 35.12273 35.15541 35.06295 35.15366 [105] 35.15089 35.11312 35.09834 35.05271 34.84838 34.52225 34.34650 34.32637 [113] 34.42911 34.79282 35.06830 35.11559 35.25736 34.43281 34.45208 34.58407 [121] 35.28598 34.34246 34.32532 34.47483 34.79309 34.02772 34.01553 35.33372 [129] 34.19273 34.07622 34.52820 35.27539 35.37703 34.70560 34.77501 34.52084 [137] 34.68773 35.19217 35.69538 34.21886 34.17226 34.94784 34.03079 33.95669 [145] 33.92002 33.92972 33.96568 33.92996 33.94236 33.93887 33.92059 33.91746 [153] 33.98369 34.17190 34.05327 33.96500 34.16136 33.98172 34.02463 34.00802 [161] 34.05238 34.05088 34.16828 34.14888 33.94711 33.96567 34.12450 33.98988 [169] 33.98670 33.98489 34.05447 34.03689 34.17137 34.31777 34.05027 33.97821 [177] 33.99281 34.00209 34.07560 33.98840 33.98930 33.98548 33.99127 35.23652 [185] 35.17034 35.53546 35.53861 34.02384 34.03402 33.93877 33.93540 33.90636 [193] 33.92267 34.57678 34.49457 34.46038 34.64318 35.06561 35.06680 34.76466 [201] 34.00418 35.48020 35.12687 35.28180 35.07281 35.23499 35.14693 34.07914 [209] 33.99047 34.00648 34.10073 34.00784 33.99185 33.98191 34.03089 33.96755 [217] 34.17042 34.10803 34.12671 34.09942 34.25003 34.06542 34.07293 34.19048 [225] 34.06594 34.01929 34.00155 34.11555 33.89754 33.89527 33.89501 33.93433 [233] 33.89881 33.94577 33.96603 33.95199 34.00284 34.12974 33.98116 34.08882 [241] 34.00953 34.98977 34.72824 34.68920 35.15207 34.59716 34.64580 34.25087 [249] 34.96008 34.62607 35.32346 35.16993 34.46759 34.47157 34.46978 34.46092 [257] 34.46561 34.46489 34.49970 34.49599 34.55441 34.52048 34.58480 34.59267 [265] 34.50082 34.57311 34.60421 34.57043 34.53131 34.46365 34.41946 34.74566 [273] 34.64593 34.67921 34.65706 34.71625 34.61487 34.61687 34.58899 34.47081 [281] 34.58366 35.66823 35.61883 34.71477 34.72518 34.69732 34.66265 34.65186 [289] 34.81468 34.74725 34.77658 34.77191 34.81481 34.76427 34.70751 34.96763 [297] 35.11322 35.16852 34.94393 34.89605 Error in xy.coords(x, y) : x and y lengths differ __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Package for multivariate binary logistic regression?
You'll have to help us a bit here. `McFadden' comes up in connection with conditional logistic regression, which package survival supports. Is that what you mean? On Tue, 30 Nov 2004, Lynne Baker wrote: I am trying to find out if someone has implemented a (McFadden-type) multivariate binary logistic regresssion package for R? From what I can tell, this is not available for R. -- Brian D. Ripley, [EMAIL PROTECTED] Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/ University of Oxford, Tel: +44 1865 272861 (self) 1 South Parks Road, +44 1865 272866 (PA) Oxford OX1 3TG, UKFax: +44 1865 272595 __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Attn Heinz Tuechler: Re: problem with sp ecial characters ( ä,ö,ü)
Thank you for the information. I did already download the 27-11-2004 version and I have the intention to try it within a day and report on the result, if this is of interest. My address ([EMAIL PROTECTED]) should work but I will check that too. Heinz Tüchler At 10:27 30.11.2004 -0500, you wrote: [I tried to send this message privately, but the return address bounced.] I think this has been fixed in R-patched, but I doubt if the fix has been tested in Win98. Could you please download a copy from http://cran.r-project.org/bin/windows/base/rpatched.html and confirm that it has been fixed? Duncan Murdoch On Sat, 27 Nov 2004 23:31:23 +0100, Heinz Tuechler [EMAIL PROTECTED] wrote : Dear Developers! Using special characters I found a strange behaviour in R 2.0.1 and equally in R : Copyright 2004, The R Foundation for Statistical Computing Version 2.0.1 (2004-11-15), ISBN 3-900051-07-0 Operating System: Windows 98SE example: factor1-as.factor(c(weiblich,männlich,österreichisch,frühreif,Gruß )) factor1 factor1 [1] weiblich m\344nnlich\366sterreichisch fr\374hreif [5] Gru\337 Levels: frühreif Gruß männlich österreichisch weiblich with best wishes Heinz Tüchler __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
RE: [R] How to know if a bug was recognised
Dear Henrik Bengtsson! Thank you for your kind answer. I am sorry that at the time of writing my inital message the last version of R was 2004-11-15. As soon as possible I will try the new version. with many thanks Heinz Tüchler At 14:01 30.11.2004 +0100, you wrote: -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Heinz Tuechler Sent: Tuesday, November 30, 2004 1:25 PM To: [EMAIL PROTECTED] Subject: [R] How to know if a bug was recognised Hello! A problem with special characters seemed to me to be a bug. I sent a mail to [EMAIL PROTECTED] concerning the problem (see below). How can I find out, if this is considered as a bug or an error of myself? Which part of FAQs or documentation did I miss to find the answer? This will not answer your question on what is a bug or not, but if you don't know, the R team has kindly made a fix for this problem. What I remember from an earlier thread, this was not really due to R, but to Windows. For the latest R v2.0.1 patch it now seems to work as before/expected: R : Copyright 2004, The R Foundation for Statistical Computing Version 2.0.1 Patched (2004-11-27), ISBN 3-900051-07-0 å [1] å ä [1] ä ö [1] ö Cheers Henrik Bengtsson thanks in advance Heinz Tüchler copy of abovementioned mail -- to: [EMAIL PROTECTED] subject: problem with special characters (ä,ö,ü) Dear Developers! Using special characters I found a strange behaviour in R 2.0.1 and equally in R : Copyright 2004, The R Foundation for Statistical Computing Version 2.0.1 (2004-11-15), ISBN 3-900051-07-0 Operating System: Windows 98SE example: factor1-as.factor(c(weiblich,männlich,österreichisch,f rühreif,Gruß )) factor1 factor1 [1] weiblich m\344nnlich\366sterreichisch fr\374hreif [5] Gru\337 Levels: frühreif Gruß männlich österreichisch weiblich with best wishes Heinz Tüchler __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] combinations min problem
Hello, as I was not yet able to find a good solution to the following problem, I'd appreciate some help. I am working on finding the minimum of a list of vectors, each comprised of x parameters to include all combinations of n parameters taken k at a time, xk thx. and rgds. a/m __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] adding regression curve to xyplot
On Tue, 30 Nov 2004, Carlisle Thacker wrote: Dear R-listers, It seems that predict() behaves differently within panel.xyplot. Am I doing something stupid? You fitted the model lm(x ~ y) and supplied new values for t, not y. Using panel.abline would be a bit easier: just call panel.abline(thislm) from your panel function. Thanks, Carlisle First, without xyplot(): lmtest - lm(t~s,data=subset(P100,whichLon100==1 whichLat100==1)) lmtest Call: lm(formula = s ~ t, data = subset(P100, whichLon100 == 1 whichLat100 == 1)) Coefficients: (Intercept)t 33.3307 0.1393 range(P100$t) [1] 4.050469 24.514543 predict(lmtest,newdata=data.frame(t=range(P100$t))) 12 33.89501 36.74620 As expected, predict gives two values. But inside xyplot() predict gives 300 values: xyplot(t~s|factor(lonLabels[whichLon100])*factor(latLabels[whichLat100]), + data=P100,pch=., + panel=function(x,y,...){panel.xyplot(x,y,...) + thislm - lm(x~y) + print(thislm) + newt - range(P100$t) + print(newt) + news - as.vector(predict(thislm,newdata=data.frame(t=newt))) + print(news) + llines(news,newt,col=red)}) Call: lm(formula = x ~ y) Coefficients: (Intercept)y 33.3307 0.1393 [1] 4.050469 24.514543 [1] 34.16173 35.31284 34.95317 35.62314 34.64448 34.06225 34.19688 34.03391 [9] 33.90860 35.28849 35.29911 34.61618 35.19837 35.28966 34.91978 35.32388 [17] 35.39351 35.54533 35.58760 34.77039 35.07226 35.35643 35.40594 33.98609 [25] 33.96461 33.91158 34.12389 34.33804 34.72235 34.63541 36.20420 36.13635 [33] 34.60623 34.32401 35.59768 34.68576 34.64661 34.58804 34.74548 35.09062 [41] 34.70290 34.22428 35.12743 34.90726 34.52325 34.90041 35.46984 34.79572 [49] 35.47026 35.35481 34.70722 34.08883 33.97586 33.94797 33.96165 33.97715 [57] 33.94886 33.99715 34.10887 34.72597 34.20534 34.45016 35.00769 34.56742 [65] 34.76119 34.87190 34.60760 34.50113 34.56594 34.65954 34.57076 34.91072 [73] 34.97322 34.99036 34.48229 34.58436 34.56767 34.94204 34.95929 34.89107 [81] 34.98846 34.51328 34.74252 34.61337 34.62212 34.70953 34.74080 34.71630 [89] 34.68599 35.58629 34.77031 34.49366 34.49873 34.48112 35.11327 34.62598 [97] 34.50436 34.50705 34.70170 35.01278 35.12273 35.15541 35.06295 35.15366 [105] 35.15089 35.11312 35.09834 35.05271 34.84838 34.52225 34.34650 34.32637 [113] 34.42911 34.79282 35.06830 35.11559 35.25736 34.43281 34.45208 34.58407 [121] 35.28598 34.34246 34.32532 34.47483 34.79309 34.02772 34.01553 35.33372 [129] 34.19273 34.07622 34.52820 35.27539 35.37703 34.70560 34.77501 34.52084 [137] 34.68773 35.19217 35.69538 34.21886 34.17226 34.94784 34.03079 33.95669 [145] 33.92002 33.92972 33.96568 33.92996 33.94236 33.93887 33.92059 33.91746 [153] 33.98369 34.17190 34.05327 33.96500 34.16136 33.98172 34.02463 34.00802 [161] 34.05238 34.05088 34.16828 34.14888 33.94711 33.96567 34.12450 33.98988 [169] 33.98670 33.98489 34.05447 34.03689 34.17137 34.31777 34.05027 33.97821 [177] 33.99281 34.00209 34.07560 33.98840 33.98930 33.98548 33.99127 35.23652 [185] 35.17034 35.53546 35.53861 34.02384 34.03402 33.93877 33.93540 33.90636 [193] 33.92267 34.57678 34.49457 34.46038 34.64318 35.06561 35.06680 34.76466 [201] 34.00418 35.48020 35.12687 35.28180 35.07281 35.23499 35.14693 34.07914 [209] 33.99047 34.00648 34.10073 34.00784 33.99185 33.98191 34.03089 33.96755 [217] 34.17042 34.10803 34.12671 34.09942 34.25003 34.06542 34.07293 34.19048 [225] 34.06594 34.01929 34.00155 34.11555 33.89754 33.89527 33.89501 33.93433 [233] 33.89881 33.94577 33.96603 33.95199 34.00284 34.12974 33.98116 34.08882 [241] 34.00953 34.98977 34.72824 34.68920 35.15207 34.59716 34.64580 34.25087 [249] 34.96008 34.62607 35.32346 35.16993 34.46759 34.47157 34.46978 34.46092 [257] 34.46561 34.46489 34.49970 34.49599 34.55441 34.52048 34.58480 34.59267 [265] 34.50082 34.57311 34.60421 34.57043 34.53131 34.46365 34.41946 34.74566 [273] 34.64593 34.67921 34.65706 34.71625 34.61487 34.61687 34.58899 34.47081 [281] 34.58366 35.66823 35.61883 34.71477 34.72518 34.69732 34.66265 34.65186 [289] 34.81468 34.74725 34.77658 34.77191 34.81481 34.76427 34.70751 34.96763 [297] 35.11322 35.16852 34.94393 34.89605 Error in xy.coords(x, y) : x and y lengths differ __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html -- Brian D. Ripley, [EMAIL PROTECTED] Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/ University of Oxford, Tel: +44 1865 272861 (self) 1 South Parks Road, +44 1865 272866 (PA) Oxford OX1 3TG, UKFax: +44 1865 272595 __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help
[R] Using mimR
Hi, I am trying to use the mimR Package. According to its help pages it needs the RDCOMClient package to run. When I try to evaluate a model I get m.sat-mim(..,data=gm.dat) Error in mim.cmd(clear; clear output) : couldn't find function COMCreate m2.sat-emfit(m.sat) Error in toMIM(mim$data) : Object m.sat not found imputeMissing() Error in mim.cmd(impute) : couldn't find function COMCreate imp.dat-retrieveData() Error in mim.cmd(pf 12,8, look.nice = FALSE) : couldn't find function COMCreate I first thought mimR might not automatically load RDCOMClient, but it turned out that RDCOMClient may not be called vie library at al, even though it was installed correctly. library(RDCOMClient) Error in library(RDCOMClient) : 'RDCOMClient' is not a valid package -- installed 2.0.0? Does anybody have an idea what the source of the problem might be? thanks and best regards Andreas __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] adding regression curve to xyplot
On Tuesday 30 November 2004 10:09, Carlisle Thacker wrote: Dear R-listers, It seems that predict() behaves differently within panel.xyplot. Am I doing something stupid? Thanks, Carlisle First, without xyplot(): lmtest - lm(t~s,data=subset(P100,whichLon100==1 whichLat100==1)) lmtest Call: lm(formula = s ~ t, data = subset(P100, whichLon100 == 1 whichLat100 == 1)) Coefficients: (Intercept)t 33.3307 0.1393 range(P100$t) [1] 4.050469 24.514543 predict(lmtest,newdata=data.frame(t=range(P100$t))) 12 33.89501 36.74620 As expected, predict gives two values. But inside xyplot() predict gives 300 values: xyplot(t~s|factor(lonLabels[whichLon100])*factor(latLabels[whichLat 100]), + data=P100,pch=., + panel=function(x,y,...){panel.xyplot(x,y,...) + thislm - lm(x~y) + print(thislm) + newt - range(P100$t) + print(newt) + news - as.vector(predict(thislm,newdata=data.frame(t=newt))) Why 't' here? The variables involved in 'thislm' are 'x' and 'y'. Deepayan + print(news) + llines(news,newt,col=red)}) [...] __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] adding regression curve to xyplot
If you only want a simple linear regression, you might also want to try xyplot(t~s|factor(lonLabels[whichLon100])*factor(latLabels[whichLat100]), + data=P100,pch=., type =c(p,r) - type r will automatically fit and plot the regression line for you. Hadley __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] adding regression curve to xyplot
On Tuesday 30 November 2004 10:24, Prof Brian Ripley wrote: On Tue, 30 Nov 2004, Carlisle Thacker wrote: Dear R-listers, It seems that predict() behaves differently within panel.xyplot. Am I doing something stupid? You fitted the model lm(x ~ y) and supplied new values for t, not y. Using panel.abline would be a bit easier: just call panel.abline(thislm) from your panel function. That wouldn't quite work, since the response and predictor are switched in the lm fit. Deepayan __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] 2k-factorial design with 10 parameters
On Tue, 30 Nov 2004, Sven wrote: I'd like to apply a 2^k factorial design with k=10 parameters. Obviously this results in a quite long term for the model equation due to the high number of combinations of parameters. How can I specify the equation for the linear model (lm) without writing all combinations explicitly down by hand? Does a R command exist for this problematic? Use expand.formula() in the AlgDesign package. -- Bob Wheeler --- http://www.bobwheeler.com/ ECHIP, Inc. --- Randomness comes in bunches. __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] adding regression curve to xyplot
On Tuesday 30 November 2004 10:18, Austin, Matt wrote: Inside the panel, you have to only use the parts of x and y for each unique combination of factor(lonLabels[whichLon100])*factor(latLabels[whichLat100]) So use thislm - lm(x[subscripts]~y[subscripts]) in the panel function. That's not true (at least in this situation). The 'x' and 'y' passed to the panel function by xyplot are already the appropriate subsets. ('groups' would have been passed whole, had it been there.) Deepayan __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] impute missing values in correlated variables: transcan?
I would like to impute missing data in a set of correlated variables (columns of a matrix). It looks like transcan() from Hmisc is roughly what I want. It says, transcan automatically transforms continuous and categorical variables to have maximum correlation with the best linear combination of the other variables. And, By default, transcan imputes NAs with best guess expected values of transformed variables, back transformed to the original scale. But I can't get it to work. I say m1 - matrix(1:20+rnorm(20),5,) # four correlated variables colnames(m1) - paste(R,1:4,sep=) m1[c(2,19)] - NA# simulate some missing data library(Hmisc) transcan(m1,data=m1) and I get Error in rcspline.eval(y, nk = nk, inclx = TRUE) : fewer than 6 non-missing observations with knots omitted I've tried a few other things, but I think it is time to ask for help. The specific problem is a real one. Our graduate admissions committee (4 members) rates applications, and we average the ratings to get an overall rating for each applicant. Sometimes one of the committee members is absent, or late; hence the missing data. The members differ in the way they use the rating scale, in both slope and intercept (if you regress each on the mean). Many decisions end up depending on the second decimal place of the averages, so we want to do better than just averging the non-missing ratings. Maybe I'm just not seeing something really simple. In fact, the problem is simpler than transcan assumes, since we are willing to assume linearity of the regression of each variable on the other variables. Other members proposed solutions that assumed this, but they did not take into account the fact that missing data at the high or low end of each variable (each member's ratings) would change its mean. Jon -- Jonathan Baron, Professor of Psychology, University of Pennsylvania Home page: http://www.sas.upenn.edu/~baron R search page: http://finzi.psych.upenn.edu/ __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Google for scientists: search engine
A new way to search for documentation on your favourite science topic. http://scholar.google.com/ http://scholar.google.com/ Alex Hanke Department of Fisheries and Oceans St. Andrews Biological Station 531 Brandy Cove Road St. Andrews, NB Canada E5B 2L9 [[alternative HTML version deleted]] __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] adding regression curve to xyplot
The axes are switched in xyplot. Oceanographers like to have temperature as the vertical axis and salinity horizontal. But temperature is used to predict salinity. Confusing, and makes everything complicated. So panel.abline(thislm) would give the wrong line, as would type=c(p,r). And neither would handle a parabolic fit. The problem was my using t rather than y when getting news. Thanks for all the help. Deepayan Sarkar wrote: On Tuesday 30 November 2004 10:24, Prof Brian Ripley wrote: On Tue, 30 Nov 2004, Carlisle Thacker wrote: Dear R-listers, It seems that predict() behaves differently within panel.xyplot. Am I doing something stupid? You fitted the model lm(x ~ y) and supplied new values for t, not y. Using panel.abline would be a bit easier: just call panel.abline(thislm) from your panel function. That wouldn't quite work, since the response and predictor are switched in the lm fit. Deepayan __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Using mimR
Andreas Cordes wrote: Hi, I am trying to use the mimR Package. According to its help pages it needs the RDCOMClient package to run. When I try to evaluate a model I get m.sat-mim(..,data=gm.dat) Error in mim.cmd(clear; clear output) : couldn't find function COMCreate m2.sat-emfit(m.sat) Error in toMIM(mim$data) : Object m.sat not found imputeMissing() Error in mim.cmd(impute) : couldn't find function COMCreate imp.dat-retrieveData() Error in mim.cmd(pf 12,8, look.nice = FALSE) : couldn't find function COMCreate I first thought mimR might not automatically load RDCOMClient, but it turned out that RDCOMClient may not be called vie library at al, even though it was installed correctly. library(RDCOMClient) Error in library(RDCOMClient) : 'RDCOMClient' is not a valid package -- installed 2.0.0? Does anybody have an idea what the source of the problem might be? That your (binary!) version of the RDCOMClient package has been installed with R 2.0.0 ? Please install a recent version compiled for R-2.0.x. A binary for R-2.0.x is available from the Omegahat webpage, or compile from sources yourself (you just need to replace one line in Makefile.win, AFAIR). Uwe Ligges thanks and best regards Andreas __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] (no subject)
Dear all, Ive got problems concerning crossed random effects and nested effects using the function lme: I have two crossed random effects and I would like to nest each of them in a fixed factor and also test for the effects of these fixed factors. At the moment my model looks like this: Lme1-lme(x~(A+B+C+D+E)^2, random=list(grp =pdBlocked(list(pdIdent(~Z-1),pdIdent(~W-1) I would like to nest Z in A and C (C/A/Z), an W in B and C (C/B/W) (A,B,C being 3 fixed factors with two levels). If you have a response to this kind of problem, could you please help me. Thank you, Anne Berthouly __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] impute missing values in correlated variables: transcan?
At the risk of stirring up a hornet's nest , I'd suggest that means are dangerous in such applications. A nice paper on combining ratings is: Gilbert Bassett and Joseph Persky, Rating Skating, JASA, 1994, 1075-1079. url:www.econ.uiuc.edu/~rogerRoger Koenker email [EMAIL PROTECTED] Department of Economics vox:217-333-4558University of Illinois fax:217-244-6678Champaign, IL 61820 On Nov 30, 2004, at 10:52 AM, Jonathan Baron wrote: I would like to impute missing data in a set of correlated variables (columns of a matrix). It looks like transcan() from Hmisc is roughly what I want. It says, transcan automatically transforms continuous and categorical variables to have maximum correlation with the best linear combination of the other variables. And, By default, transcan imputes NAs with best guess expected values of transformed variables, back transformed to the original scale. But I can't get it to work. I say m1 - matrix(1:20+rnorm(20),5,) # four correlated variables colnames(m1) - paste(R,1:4,sep=) m1[c(2,19)] - NA# simulate some missing data library(Hmisc) transcan(m1,data=m1) and I get Error in rcspline.eval(y, nk = nk, inclx = TRUE) : fewer than 6 non-missing observations with knots omitted I've tried a few other things, but I think it is time to ask for help. The specific problem is a real one. Our graduate admissions committee (4 members) rates applications, and we average the ratings to get an overall rating for each applicant. Sometimes one of the committee members is absent, or late; hence the missing data. The members differ in the way they use the rating scale, in both slope and intercept (if you regress each on the mean). Many decisions end up depending on the second decimal place of the averages, so we want to do better than just averging the non-missing ratings. Maybe I'm just not seeing something really simple. In fact, the problem is simpler than transcan assumes, since we are willing to assume linearity of the regression of each variable on the other variables. Other members proposed solutions that assumed this, but they did not take into account the fact that missing data at the high or low end of each variable (each member's ratings) would change its mean. Jon -- Jonathan Baron, Professor of Psychology, University of Pennsylvania Home page: http://www.sas.upenn.edu/~baron R search page: http://finzi.psych.upenn.edu/ __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] about the subscript assignment porblem
Hi, Dear, I have a problem for the new version 2.0 of R When I put this code in it give me the error: uis$ivhx3[uis$ivhx0] - 1*(uis$ivhx==3) Error: NAs are not allowed in subscripted assignments but this would happen in version 1.91 there are missing data in the data set and it is represented as NA the data set can be find on line at the ucla web actually this is a example from its web site the c code is at https://svn.r-project.org/R/trunk/src/main/subassign.c : if(length(y) 1) for(i = 0; i n; i++) if(INTEGER(indx)[i] == NA_INTEGER) error(NAs are not allowed in subscripted assignments); So maybe we need get rid of this conditional code. Best Wishes Ku __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] impute missing values in correlated variables: transcan?
On 11/30/04 11:23, roger koenker wrote: At the risk of stirring up a hornet's nest , I'd suggest that means are dangerous in such applications. A nice paper on combining ratings is: Gilbert Bassett and Joseph Persky, Rating Skating, JASA, 1994, 1075-1079. Here is the abstract, which seems to capture what the article says: Among judged sports, figure skating uses a unique method of median ranks for determining placement. This system responds positively to increased marks by each judge and follows majority rule when a majority of judges agree on a skater's rank. It is demonstrated that this is the only aggregation system possessing these two properties. Median ranks provide strong safeguards against manipulation by a minority of judges. These positive features do not require the sacrifice of efficiency in controlling measurement error. In a Monte Carlo study, the median rank system consistently outperforms alternatives when judges' marks are significantly skewed toward an upper limit. I think this is irrelevant. We are using ratings, not rankings. (And there was a small error in my original post. The disturbing effect of missing data at the high or low end would be on the slope rather than the intercept or mean.) Jon -- Jonathan Baron, Professor of Psychology, University of Pennsylvania Home page: http://www.sas.upenn.edu/~baron __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] RecordPlot
I want to do a zoom with recordPlot(). I have problems with lists. (R-2.0.1 patched 2004-11-30 , various linux). I have problems with RecordPlot class structure. plot(1:10) saveP - recordPlot() dev.off() sx - saveP[[1]][[2]][[2]] saveP[[1]][[2]][[2]] - sx Error in [[-(`*tmp*`, 1, value = list(list( .Primitive(plot.new)), list(.Primitive(plot .window), c(1, : incompatible types typeof(saveP[[1]][[2]][[2]]) [1] double typeof(sx) [1] double But: s1 - saveP[[1]] s1[[2]][[2]] - c(4,6) saveP[1] - list(s1) saveP # zoom is OK Also, I don't understand recursive indexing. With not modified saveP, saveP[[c(1,2)]] [[1]] .Primitive(plot.window) [[2]] [1] 1 10 [[3]] [1] 1 10 [[4]] [1] [[5]] [1] NA # OK saveP[[c(1,2,2)]] Error: recursive indexing failed at level 2 # why not [1] 1 10 ?? Jean Coursol __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] A basic question
On gentoo: emerge R and dowload,configuration, compilation of all you need to working with base R is performed. Best! A.S. Alessandro Semeria Models and Simulations Laboratory Montecatini Environmental Research Center (Edison Group), Via Ciro Menotti 48, 48023 Marina di Ravenna (RA), Italy Tel. +39 544 536811 Fax. +39 544 538663 E-mail: [EMAIL PROTECTED] Kenneth [EMAIL PROTECTED] Sent by: [EMAIL PROTECTED] 30/11/2004 12.58 To: [EMAIL PROTECTED] cc: Subject:[R] A basic question Hi R users: I want to know any experience compiling R in other LINUX distributions besides FEDORA (Red Hat) or Mandrake, for example in BSD, Debian, Gentoo, Slackware, vector LINUX, Knoppix, Yopper or CERN linux? Hope this is not a basic question Thank you for your help. Kenneth __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html [[alternative HTML version deleted]] __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Course ****R/S System: Advanced Programming, Seattle***December 20-21
R/S Advanced Programming course in Seattle on December 20-21 Please check out the full description and Agenda of the 2-day class on the website: www.xlsolutions-corp.com/Radv.htm And let us know if we should hold seats for you. Ask for group discount! Here's the outline: Course outline: - Overview of R/S fundamentals: Syntax and Semantics - Class and Inheritance in R/S-Plus - Concepts, Construction and good use of language objects - Coercion and efficiency - Object-oriented programming in R and S-Plus - Advanced manipulation tools: Parse, Deparse, Substitute, etc. - How to fully take advantage of Vectorization - Generic and Method Functions; S4 (S-Plus 6) - Search path, databases and frames Visibility - Working with large objects - Handling Properly Recursion and iterative calculations - Managing loops; For (S-Plus) and for() loops - Consequences of Lazy Evaluation - Efficient Code practices for large computations - Memory management and Resource monitoring - Writing R/S-Plus functions to call compiled code - Writing and debugging compiled code for R/S-Plus system - Connecting R/S-Plus to External Data Sources - Understanding the structure of model fitting functions in R/S-Plus - Designing and Packaging efficiently This course will also deal with lots of S-Plus efficiency issues and any special topics from participants is welcome. Please let us know if you and your colleagues are interested in this class to take advantage of group discount. Register now to secure your seat in this course! Cheers, Elvis Miller, PhD Manager Training. XLSolutions Corporation 206 686 1578 www.xlsolutions-corp.com __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] about the subscript assignment porblem
On Tue, 30 Nov 2004, kh zu wrote: Hi, Dear, I have a problem for the new version 2.0 of R When I put this code in it give me the error: uis$ivhx3[uis$ivhx0] - 1*(uis$ivhx==3) Error: NAs are not allowed in subscripted assignments but this would happen in version 1.91 What would happen? In version 1.9.0 (I don't have a 1.9.1 lying around) you get a warning if any of the subscripts are FALSE x-1:3 y-7:9 x[c(TRUE,NA,FALSE)]-y Warning message: number of items to replace is not a multiple of replacement length and if all the subscripts are TRUE or NA the NAs are treated as FALSE x-1:3 y-7:9 x[c(TRUE,NA,TRUE)]-y x [1] 7 2 9 The change was largely motivated by numerical indices, where the problem is worse. In particular if x is 1,2,3, i is 1, NA, 2 and y is 7,8,9, should x[i] - y set the second element of x to 8 or 9? The answer was different for vectors and matrices in 1.9.1. It was clearly a deliberate change, not a mistake (it's hard to see how it could have happened accidentally, and it was documented), and the previous behaviour was wrong. -thomas __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] impute missing values in correlated variables: transcan?
Jonathan Baron wrote: I would like to impute missing data in a set of correlated variables (columns of a matrix). It looks like transcan() from Hmisc is roughly what I want. It says, transcan automatically transforms continuous and categorical variables to have maximum correlation with the best linear combination of the other variables. And, By default, transcan imputes NAs with best guess expected values of transformed variables, back transformed to the original scale. But I can't get it to work. I say m1 - matrix(1:20+rnorm(20),5,) # four correlated variables colnames(m1) - paste(R,1:4,sep=) m1[c(2,19)] - NA# simulate some missing data library(Hmisc) transcan(m1,data=m1) and I get Error in rcspline.eval(y, nk = nk, inclx = TRUE) : fewer than 6 non-missing observations with knots omitted Jonathan - you would need many more observations to be able to fit flexible additive models as transcan does. Also note that single imputation has problems and you may want to consider multiple imputation as done by the Hmisc aregImpute function, if you had more data. Frank I've tried a few other things, but I think it is time to ask for help. The specific problem is a real one. Our graduate admissions committee (4 members) rates applications, and we average the ratings to get an overall rating for each applicant. Sometimes one of the committee members is absent, or late; hence the missing data. The members differ in the way they use the rating scale, in both slope and intercept (if you regress each on the mean). Many decisions end up depending on the second decimal place of the averages, so we want to do better than just averging the non-missing ratings. Maybe I'm just not seeing something really simple. In fact, the problem is simpler than transcan assumes, since we are willing to assume linearity of the regression of each variable on the other variables. Other members proposed solutions that assumed this, but they did not take into account the fact that missing data at the high or low end of each variable (each member's ratings) would change its mean. Jon -- Frank E Harrell Jr Professor and Chair School of Medicine Department of Biostatistics Vanderbilt University __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] xy_plot
R users; Does anyone have a recommendation for a faster plotting function rather than plot(x,y)? when I use plot(x,y) for a large number of variables, it take couple of moments to plot the graph? Sincerely, Sean __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] New trellis settings
On Mon, Nov 29, 2004 at 11:23:35PM -0600, Deepayan Sarkar wrote: Specifically, I have some code that in the past changed the relative proportions of text versus the plot area using: trellis.par.set('fontsize', list(text=8)) which caused all text to get smaller, and the plot area to grow to fill the larger available space. Now, the plot area does not grow on its own. That does seem to have been a side-effect in 1.9.1, but it was never intended. I would consider that behaviour a bug, not a feature. It was a pretty convenient bug! ;) str(trellis.par.get()$layout.heights) List of 18 $ top.padding : num 1 $ main : num 1 $ main.key.padding : num 1 $ key.top : num 1 $ key.axis.padding : num 1 ... I was hoping that the names would be enough of a hint. Anything with 'padding' in the name is space, and probably the ones you want to change. I've fiddled with these and can pretty much get what I want. But without really understanding what I'm doing. It isn't clear to me, for instance, why the key settings affect my plot when no key is drawn. -- Dave __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] A basic question
R has compiled with no problem in FreeBSD. It is also included in the ports, thanks to its FreeBSD maintainer. Andrew On Tue, Nov 30, 2004 at 06:58:57AM -0500, Kenneth wrote: Hi R users: I want to know any experience compiling R in other LINUX distributions besides FEDORA (Red Hat) or Mandrake, for example in BSD, Debian, Gentoo, Slackware, vector LINUX, Knoppix, Yopper or CERN linux? Hope this is not a basic question Thank you for your help. Kenneth __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html -- Andrew Robinson Ph: 208 885 7115 Department of Forest Resources Fa: 208 885 6226 University of Idaho E : [EMAIL PROTECTED] PO Box 441133W : http://www.uidaho.edu/~andrewr Moscow ID 83843 Or: http://www.biometrics.uidaho.edu No statement above necessarily represents my employer's opinion. __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] RecordPlot
Hi The main problem here is that you really shouldn't be poking around inside a recordedplot object. From the help page: WARNING: The format of recorded plots may change between R versions. Recorded plots should *not* be used as a permanent storage format for R plots. R will always attempt to replay a recorded plot, but if the plot was recorded with a different R version then bad things may happen. This could (should) be more explicit. In particular, it might be worth adding a comment from the C source ... * The graphics engine assumes that it is getting a snapshot * that was created in THE CURRENT R SESSION ... [snapshot == recordedplot]. The basic message is: don't rely on the internal structure of a recordedplot because we can (and have [and will]) change it at any time. That leaves the problem of how to achieve your zoom, but I'm not sure exactly what your zoom is doing (just modifying the axis ranges?). Could you (privately) send me screen shots of before and after the zoom? Then I can try to suggest a correct way to zoom. Paul Jean Coursol wrote: I want to do a zoom with recordPlot(). I have problems with lists. (R-2.0.1 patched 2004-11-30 , various linux). I have problems with RecordPlot class structure. plot(1:10) saveP - recordPlot() dev.off() sx - saveP[[1]][[2]][[2]] saveP[[1]][[2]][[2]] - sx Error in [[-(`*tmp*`, 1, value = list(list( .Primitive(plot.new)), list(.Primitive(plot .window), c(1, : incompatible types typeof(saveP[[1]][[2]][[2]]) [1] double typeof(sx) [1] double But: s1 - saveP[[1]] s1[[2]][[2]] - c(4,6) saveP[1] - list(s1) saveP # zoom is OK Also, I don't understand recursive indexing. With not modified saveP, saveP[[c(1,2)]] [[1]] .Primitive(plot.window) [[2]] [1] 1 10 [[3]] [1] 1 10 [[4]] [1] [[5]] [1] NA # OK saveP[[c(1,2,2)]] Error: recursive indexing failed at level 2 # why not [1] 1 10 ?? Jean Coursol __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html -- Dr Paul Murrell Department of Statistics The University of Auckland Private Bag 92019 Auckland New Zealand 64 9 3737599 x85392 [EMAIL PROTECTED] http://www.stat.auckland.ac.nz/~paul/ __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] impute missing values in correlated variables: transcan?
On 11/30/04 13:21, Frank E Harrell Jr wrote: Jonathan Baron wrote: I would like to impute missing data in a set of correlated variables (columns of a matrix). It looks like transcan() from Hmisc is roughly what I want. It says, transcan automatically transforms continuous and categorical variables to have maximum correlation with the best linear combination of the other variables. And, By default, transcan imputes NAs with best guess expected values of transformed variables, back transformed to the original scale. But I can't get it to work. I say m1 - matrix(1:20+rnorm(20),5,) # four correlated variables colnames(m1) - paste(R,1:4,sep=) m1[c(2,19)] - NA# simulate some missing data library(Hmisc) transcan(m1,data=m1) and I get Error in rcspline.eval(y, nk = nk, inclx = TRUE) : fewer than 6 non-missing observations with knots omitted Jonathan - you would need many more observations to be able to fit flexible additive models as transcan does. Also note that single imputation has problems and you may want to consider multiple imputation as done by the Hmisc aregImpute function, if you had more data. Thanks. But they don't _need_ to be so flexible as what transcan does. Linear would be OK, but I can't find an option for that in transcan. We _will_ have more data, about 50 applicants rated by the time we start making decisions. So I tried my little simulation with more data, and it didn't give an error message. So that was the problem. Here is the new one: m1 - matrix(1:80+rnorm(80),,4) colnames(m1) - paste(R,1:4,sep=) m1[c(2,19)] - NA library(Hmisc) t1 - transcan(m1,data=m1,long=T,imputed=T) I've used aregImpute, and I notice it has a defaultlinear option, which is good. Thus, it may work better once I figure out how to get a single value out of it for each missing datum (which doesn't look too hard). This is not about statistical inference, which seems to me to be where the main advantage of multiple imputation lies. But probably it won't do any harm. Jon -- Jonathan Baron, Professor of Psychology, University of Pennsylvania Home page: http://www.sas.upenn.edu/~baron R search page: http://finzi.psych.upenn.edu/ __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] xy_plot
Sean: You need to provide more information on your problem for anyone to help you much. One of the apply functions working in tandem with points or lines (or others) can often do multiple item quickly, but again I don't know the context of your problem. Mike - Original Message - From: ebashi [EMAIL PROTECTED] To: R [EMAIL PROTECTED] Sent: Tuesday, November 30, 2004 2:31 PM Subject: [R] xy_plot R users; Does anyone have a recommendation for a faster plotting function rather than plot(x,y)? when I use plot(x,y) for a large number of variables, it take couple of moments to plot the graph? Sincerely, Sean __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Random effects and non-linear models
I am trying to model growth over time for a number of companies (my unit of analysis). My dependent variable is a count (the number of acquisitions each firm made each year), and I'm having some trouble figuring out exactly how to model this. My assumption is that modeling the effect of time on this dependent variable with a linear model is inappropriate. Does anyone have any guidance regarding how to model such a dependent variable such that I could include both random and fixed effects? Thanks in advance. S. Trevis Certo, PhD Assistant Professor Mays Research Fellow Management Department Mays Business School Texas AM University [[alternative HTML version deleted]] __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] augPred with lme(...,subset=...)
Hello, Is there a way to get augPred to work with lme if a subset statement is used? For example, if I modify the example from ?augPred.lme to include a subset statement, I get the following error: fm1 - lme(Orthodont, random = ~1, subset=distance19) augPred(fm1, length.out = 2, level = c(0,1)) Error in tapply(object[[nm]], groups, FUN[[numeric]], ...) : arguments must have same length Thanks! Manuel __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Reading a tab delimitted text
Dear group, I have a tab delimitted text file with 21 column and 1988 rows. When I read the file: D1 - read.table(file=gist_data1.txt,sep=\t,header=T) dim(D1) [1] 1811 20 It reads only 1811 rows from that file. I saved this file as CSV file and I read it again using: D1 - read.csv(file=gist_data1.txt,sep=,,header=T) dim(D1) [1] 19871 This timer it reaad correct number of rows and wrong column numbers. Can any one suggest how to read a tab-delimited text file and read in corect number of lines. thank you. __ The all-new My Yahoo! - What will yours do? __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] bitmap (blank image) plot rendering without X11
Hi, I am trying to generate plots on our unix (no X) server to be included in our web-pages - specifically pngs. Without X, png() obviously doesn't work, so I have been trying to define the graphics print device bitmap as described in the help: bitmap(file=plot.png, type = png256, height = 6, width=6,res=72) pie(c(12,5)) dev2bitmap(file=plot.png, type = png256, height = 6, width = 6,res=72) I end up with plot.png as a nonzero png file, but it is always blank... I have gs 6.51 installed R_GSCMD=/usr/bin/gs set. generating Rplot.ps; pstoimg -antialias (or pstopnm) would also be an acceptable solution if I knew how to control the size of the generated image, or if the ps generated by R was consistently compatible with pstopnm. (ps2ps causes me to lose parts of the image).. So I am asking know-alls of R... if they know of a solution? We are generating thousands of images, so work on a windows or slower machine with X is not really an option... any help much appreciated! Beracah -- Beracah Yankama Director, StudentsReview StudentsReview.com [EMAIL PROTECTED] __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Relative subscripting
Hi! I'm trying to do the following. I have monthly a dataset with, among other things, marketcap, and return. I want to multiply return by the marketcap of the previous month. How do I do this? In STATA (which I have used frequently in the past) I would simply use an expression of the form return[_n]*marketcap[_n-1] I believe they call this relative subscripting. Is there something like this in R? On a completely different note, are there books on R? I read the Getting Started notes, but, while helpful, I would need more than those. Thanks, Toby __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] SJava
How can I increase the JVM's memory using teh SJava library? __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] calling R from Java
Greetings, I would like to call a small R function from Java (actually to Bioconductor). From a little reading, looks like I can only do this on a Unix system and not on a PC. Is this indeed the case? Does anyone have experience with calling a R function from Java? Lana Lana Schaffer Research Specialist The Scripps Research Institute DNA Array Core Facility __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Package for multivariate binary logistic regression?
Lynne Baker wrote: I am trying to find out if someone has implemented a (McFadden-type) multivariate binary logistic regresssion package for R? From what I can tell, this is not available for R. Thank you, Lynne Baker [[alternative HTML version deleted]] __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html You can have a look at package VGAM (I think still not on CRAN) which has binom2.or, for instance. Kjetil Halvorsen -- Kjetil Halvorsen. Peace is the most effective weapon of mass construction. -- Mahdi Elmandjra __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Choice modelling (was:(no subject))
[EMAIL PROTECTED] wrote: Hello, I am trying to estimate a choice model with varying choice set for each individual. I would like to fit different kinds of model (logit ,nested logit, probit...). So far I have found that package *mnp* allows me to estimate a probit model with varying choice set. But for estimation of a logit model, I have only found function *multinom* of package *nnet* which does not seem to allow for varying choice set. I could incorporate indicators of choice availability as explanotary variables, but it does not seem a very good way to do it. Instead, for a logit model, I have coded a likelihood computation of the underlying model with varying choice set and I use optim function to get the maximum. Could you post the code? I wondered if there were more user friendly functions available and/or other choice model related package. Look at CRAN package eba (elimination by aspects). Kjetil Thanks, Julien __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html -- Kjetil Halvorsen. Peace is the most effective weapon of mass construction. -- Mahdi Elmandjra __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] bitmap (blank image) plot rendering without X11
Director, Beracah Yankama [EMAIL PROTECTED] writes: Hi, I am trying to generate plots on our unix (no X) server to be included in our web-pages - specifically pngs. Without X, png() obviously doesn't work, so I have been trying to define the graphics print device bitmap as described in the help: bitmap(file=plot.png, type = png256, height = 6, width=6,res=72) pie(c(12,5)) dev2bitmap(file=plot.png, type = png256, height = 6, width = 6,res=72) I end up with plot.png as a nonzero png file, but it is always blank... I have gs 6.51 installed R_GSCMD=/usr/bin/gs set. Try forgetting the dev2bitmap() line and just terminate the device with dev.off(). -- O__ Peter Dalgaard Blegdamsvej 3 c/ /'_ --- Dept. of Biostatistics 2200 Cph. N (*) \(*) -- University of Copenhagen Denmark Ph: (+45) 35327918 ~~ - ([EMAIL PROTECTED]) FAX: (+45) 35327907 __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] seriesMerge
I want to merge two timeSeries (union) and get a resulting timeSeries. using union or merge I got a data.frame and when I tried to convert it to timeSeries the data was corrupt. Is there a more straight forward way to take two timeSeries and merege them for a resulting timeSeries of the union of both? On Thu, 25 Nov 2004 03:50:28 + (UTC), Gabor Grothendieck [EMAIL PROTECTED] wrote: Yasser El-Zein abu3ammar at gmail.com writes: : : Is there a function in R that is equivalent to S-PLUS's : seriesMerge(x1, x2, pos=union) : where x1, and x2 are of class timeSeries : : seriesMerge is in S-PLUS's finmetrics. I looked into R's mergeSeries : (in fSeries part of Rmetrics) but I could not make it behave quite the : same. In R it expected a timeSeries object and a matrix of the same : row count. In S-PLUS when using the union option both objects can be : of different lengths. merge.zoo in package zoo handles union, intersection, left and right join of unequal length time series according to the setting of the all= argument. zoo can also work with chron dates and times which would allow you to work with your millisecond data and can also merge more than two series at a time. (The its package (see ?itsJoin) and for regular time series, cbind.ts, also support merging unequal length series but neither of these support chron which I gather is a requirement for you.) eg. zoo example. In the following x has length 8 and y has length 6 and they overlap for chron(5:8). chron(1:4) only belongs to x and chron(9:10) only belongs to y. library(chron) library(zoo) x - zoo(1:8, chron(1:8)) y - zoo(5:10, chron(5:10)) merge(x,y) # union merge(x,y,all=FALSE) # intersection merge(x,y,all=c(FALSE, TRUE)) # right join merge(x,y,all=c(TRUE, FALSE)) # left join __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Relative subscripting
wouldn't it be return[2:NROW(return)]*marketcap[1:(NROW(return)-1)] (note that return is also a function in R so maybe you should stay away from calling your variable return. Anyways if you have a data frame you can add another variable to it but attach an NA to the first element (since you are lagging variables) i.e. mydata$myvar-c(NA, mydata$return[2:nrow(mydata)]*mydata$marketcap[1:(nrow(mydata)-1)] Jean On Tue, 30 Nov 2004, Tobias Muhlhofer wrote: Hi! I'm trying to do the following. I have monthly a dataset with, among other things, marketcap, and return. I want to multiply return by the marketcap of the previous month. How do I do this? In STATA (which I have used frequently in the past) I would simply use an expression of the form return[_n]*marketcap[_n-1] I believe they call this relative subscripting. Is there something like this in R? On a completely different note, are there books on R? I read the Getting Started notes, but, while helpful, I would need more than those. Thanks, Toby __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Relative subscripting
Tobias Muhlhofer wrote: Hi! I'm trying to do the following. I have monthly a dataset with, among other things, marketcap, and return. I want to multiply return by the marketcap of the previous month. How do I do this? In STATA (which I have used frequently in the past) I would simply use an expression of the form return[_n]*marketcap[_n-1] I believe they call this relative subscripting. Is there something like this in R? On a completely different note, are there books on R? I read the Getting Started notes, but, while helpful, I would need more than those. Q 2.7 in the R faq (yes, there are many)! Kjetil Thanks, Toby __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html -- Kjetil Halvorsen. Peace is the most effective weapon of mass construction. -- Mahdi Elmandjra __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Relative subscripting
OK, yeah. I did think of that in the meantime, but I was also wondering if there was some other convenience function to do it. But this will do in any case. Toby Jean Eid wrote: wouldn't it be return[2:NROW(return)]*marketcap[1:(NROW(return)-1)] (note that return is also a function in R so maybe you should stay away from calling your variable return. Anyways if you have a data frame you can add another variable to it but attach an NA to the first element (since you are lagging variables) i.e. mydata$myvar-c(NA, mydata$return[2:nrow(mydata)]*mydata$marketcap[1:(nrow(mydata)-1)] Jean On Tue, 30 Nov 2004, Tobias Muhlhofer wrote: Hi! I'm trying to do the following. I have monthly a dataset with, among other things, marketcap, and return. I want to multiply return by the marketcap of the previous month. How do I do this? In STATA (which I have used frequently in the past) I would simply use an expression of the form return[_n]*marketcap[_n-1] I believe they call this relative subscripting. Is there something like this in R? On a completely different note, are there books on R? I read the Getting Started notes, but, while helpful, I would need more than those. Thanks, Toby __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html -- ** When Thomas Edison invented the light bulb he tried over 2000 experiments before he got it to work. A young reporter asked him how it felt to have failed so many times. He said I never failed once. I invented the light bulb. It just happened to be a 2000-step process. __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Random effects and non-linear models
Certo, Trevis wrote: I am trying to model growth over time for a number of companies (my unit of analysis). My dependent variable is a count (the number of acquisitions each firm made each year), and I'm having some trouble figuring out exactly how to model this. My assumption is that modeling the effect of time on this dependent variable with a linear model is inappropriate. Does anyone have any guidance regarding how to model such a dependent variable such that I could include both random and fixed effects? Thanks in advance. You may want to consider a generalized linear mixed model (GLMM) for the Poisson family. These can be fit with the GLMM function in the lme4 package. __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
RE: [R] Relative subscripting
On 30-Nov-04 Tobias Muhlhofer wrote: [...] I have monthly a dataset with, among other things, marketcap, and return. I want to multiply return by the marketcap of the previous month. How do I do this? In STATA (which I have used frequently in the past) I would simply use an expression of the form return[_n]*marketcap[_n-1] I believe they call this relative subscripting. Is there something like this in R? Not as such, as far as I know. But there's an easy way to achieve the same effect: Let N-length(return) new.var - return[2:N]*marketcap[1:(N-1)] Notes: 1. Note the parantheses in 1:(N-1). 1:(6-1) [1] 1 2 3 4 5 1:6-1 [1] 0 1 2 3 4 5 (i.e. : is evaluated before -) 2. You could also define n - 2:(N-1) in which case you could definitely write return[n]*marketcap[n-1] which looks very similar to what you wrote, but I don't know whether it implies the same underlying mechanism. 3. I'm not sure you should use return as the name of a variable, since it's a predefined function in R, which you can put in a function definition to tell it what to return: sq-function(x){return(x^2)} sq(4) [1] 16 In my experiments, it didn't seem to change this behaviour to assign something to return, e.g. return-2, even inside the function definition; but I'd recommend avoiding the practice! You could avoid it here by using Return instead of return for the name of your variable. Best wishes, Ted. E-Mail: (Ted Harding) [EMAIL PROTECTED] Fax-to-email: +44 (0)870 094 0861 [NB: New number!] Date: 30-Nov-04 Time: 21:34:02 -- XFMail -- __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] augPred with lme(...,subset=...)
Manuel Morales wrote: Hello, Is there a way to get augPred to work with lme if a subset statement is used? For example, if I modify the example from ?augPred.lme to include a subset statement, I get the following error: fm1 - lme(Orthodont, random = ~1, subset=distance19) augPred(fm1, length.out = 2, level = c(0,1)) Error in tapply(object[[nm]], groups, FUN[[numeric]], ...) : arguments must have same length Thanks! Manuel __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html Well you could debug the augPred method and send the package maintainer a patch :-) __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Reading a tab delimitted text
Srinivas Iyyer wrote: Dear group, I have a tab delimitted text file with 21 column and 1988 rows. When I read the file: D1 - read.table(file=gist_data1.txt,sep=\t,header=T) dim(D1) [1] 1811 20 It reads only 1811 rows from that file. I saved this file as CSV file and I read it again using: D1 - read.csv(file=gist_data1.txt,sep=,,header=T) dim(D1) [1] 19871 This timer it reaad correct number of rows and wrong column numbers. Can any one suggest how to read a tab-delimited text file and read in corect number of lines. thank you. Check for the presence of unexpected comment characters or quote characters in the file you are reading. Alternatively, try setting quote='', comment='' in the call to read.table. __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] New trellis settings
On Tuesday 30 November 2004 13:33, David Hinds wrote: On Mon, Nov 29, 2004 at 11:23:35PM -0600, Deepayan Sarkar wrote: Specifically, I have some code that in the past changed the relative proportions of text versus the plot area using: trellis.par.set('fontsize', list(text=8)) which caused all text to get smaller, and the plot area to grow to fill the larger available space. Now, the plot area does not grow on its own. That does seem to have been a side-effect in 1.9.1, but it was never intended. I would consider that behaviour a bug, not a feature. It was a pretty convenient bug! ;) str(trellis.par.get()$layout.heights) List of 18 $ top.padding : num 1 $ main : num 1 $ main.key.padding : num 1 $ key.top : num 1 $ key.axis.padding : num 1 ... I was hoping that the names would be enough of a hint. Anything with 'padding' in the name is space, and probably the ones you want to change. I've fiddled with these and can pretty much get what I want. But without really understanding what I'm doing. It isn't clear to me, for instance, why the key settings affect my plot when no key is drawn. It shouldn't (unless you have messed with lattice.options()). Can you provide an example? The following doesn't do anything unusual for me: xyplot(1~1, par.settings = list(layout.heights = list(key.top = 100, key.bottom = 100))) (I'm running r-devel though, so there's a small chance something might be different.) Deepayan __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Combined variable names
I am trying to define a large number of variables through a loop construct. I have my loop variable i being cycled through 1:100 and I would like the variables produced by this to be called vi (i.e. v1 v2 v3 etc) so, for example I'm going: for(i in 1:100) { blank - a[i:N] # or whatever else you want to put on the right side } where N is previously defined. What goes in for blank? Thanks, Toby __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] nls() error: Object not found
Dear R-helpers; Using nls() to fit a function,Rdum, defined below I stumbled on an error: Error in eval(expr, envir, enclos): Object s0 not found. The function Rdum is defined as Rdum - deriv(~ h1 * (s0 + sl0*sl + sm0*sm + sp01*sp1 + sp02*sp2 + sp03*sp3+sp04*sp4) * ((1 - exp(-(s1 + sl1*sl + sm1*sm + sp11*sp1 + sp12*sp2 + sp14*sp4)*t2)) / (1 - exp(-(s1 + sl1*sl + sm1*sm + sp11*sp1 + sp12*sp2 + sp14*sp4)*t1)))^ (s2 + sl2*sl+sm2*sm+ sp21*sp1+sp22*sp2+sp23*sp3+sp24*sp4), c(s0, s10,sm0, sp01,sp02,sp03,sp04, s1, sl1,sm1, sp11, sp12,sp14, s2,sl2,sm2, sp21,sp22,sp23,sp24), function(s0,sl0,sm0,sp01,sp02,sp03,sp04, s1, sl1, sm1, sp11,sp12, sp14, s2, sl2, sm2, sp21,sp22, sp23, sp24, h1, t1,t2, sl, sm,sp1, sp2, sp3, sp4){}) and variables t1, t2, h1, h2, sl, sm, sp1, sp2, sp3, and sp4 in the gbht10D data frame are fitted to the function by Dum.nls - nls(h2 ~ Rdum(s0, sl0, sm0, sp01, sp02, sp03, sp04, sl, sl1,sm1,sp11,sp12, sp14, s2, sl2, sm2, sp21, sp22, sp23, sp24,h1, t1, t2, sl, sm, sp1, sp2, sp3, sp4), data=gbht10D, start=c(0.8413,-0.1602,-0.0156,0.0527,0.0513,0.00314,0.0378, -0.00598,-0.0125,0.00328,0.00989,0.0113,0.00583, 1.9255,0.9427,0.2408,-0.0643,0.0047,0.0016,-0.00519)) The complained object s0 is one of the 20 parameters in the function to be estimated from the dataset gbht10D. The nls() script is relatively short. Stepping into the source code, I located the offending line: Browse[1] start [1] 0.84130 -0.16020 -0.01560 0.05270 0.05130 0.00314 0.03780 -0.00598 -0.01250 [10] 0.00328 0.00989 0.01130 0.00583 1.92550 0.94270 0.24080 -0.06430 0.00470 [19] 0.00160 -0.00519 Browse[1] n debug: pnames - names(start) Browse[1] n debug: varNames - varNames[is.na(match(varNames, pnames, nomatch = NA))] Browse[1] n debug: varIndex - sapply(varNames, function(varName, data, respLength) { length(eval(as.name(varName), data))%%respLength == 0 }, data, length(eval(formula[[2]], data))) Browse[1] varNames [1] h2 s0 sl0 sm0 sp01 sp02 sp03 sp04 sl sl1 sm1 sp11 [13] sp12 sp14 s2 sl2 sm2 sp21 sp22 sp23 sp24 h1 t1 t2 [25] sm sp1 sp2 sp3 sp4 Browse[1] n Error in eval(expr, envir, enclos) : Object s0 not found. The s0 is shown in varNames. Is the error message misleading? Or did I miss something? Any iedas and suggestions? I am using R 2.0.0 on Windows XP. TIA, Richard Yang __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Combined variable names
On Tue, 30 Nov 2004, Tobias Muhlhofer wrote: I am trying to define a large number of variables through a loop construct. I have my loop variable i being cycled through 1:100 and I would like the variables produced by this to be called vi (i.e. v1 v2 v3 etc) Look at FAQ 7.21, which explains how to do it and suggest that you might not really want to. -thomas __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] predict.gam problem
- Mac OS X 10.3 R 2.0.1 gam 0.9.2 - Greetings I am facing difficulties in prediction on using Trevor Hasties GAM package. How can one interpret the response from predict.gam? Documentation on the type-parameter: The default (link) produces predictions on the scale of the additive predictors, ... If response is selected, the predictions are on the scale of the response, and are monotone trans-formations of the additive predictors, using the inverse link function. Does on the scale of the response ammount to residals? All I want to do is get the predicted response from running my GAM model on new data. The results given are way off, but I am not able to dechipher the documentation, nor use any scale information. Any help will be highly appreciated. All the best Jon Egil Strand -- Jon Egil Strand [EMAIL PROTECTED] Phone: +47 45030081 __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Combined variable names
See the R-FAQ here: http://cran.r-project.org/doc/FAQ/R-FAQ.html Number 7.21. However, as the FAQ also points out, you might be better served using lists. a - list() for (i in 1:100) { a[[i]] - some stuff } Sean On Nov 30, 2004, at 5:42 PM, Tobias Muhlhofer wrote: I am trying to define a large number of variables through a loop construct. I have my loop variable i being cycled through 1:100 and I would like the variables produced by this to be called vi (i.e. v1 v2 v3 etc) so, for example I'm going: for(i in 1:100) { blank - a[i:N] # or whatever else you want to put on the right side } where N is previously defined. What goes in for blank? Thanks, Toby __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ [EMAIL PROTECTED] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html