[R] How could plot a chart with some Chinese's words text?
Dear all, I want to plot a chart title with some Chinese words at unix system, but I do not how to do. first, it is no problem when I use write.table like: a- write.table(a,file=z.txt,sep=\t) second, I try bitmap(file=z.png) plot(1:10,main=a) dev.off() I can't get a chart with the right title = Why have this difference? Thanks a lot ken __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] How could plot a chart with some Chinese's words text?
On Mon, 30 Jun 2003, Ken Lee wrote: Dear all, I want to plot a chart title with some Chinese words at unix system, but I do not how to do. first, it is no problem when I use write.table like: a-中文 write.table(a,file=z.txt,sep=\t) Not, that is not Chinese for me and I suspect almost all your readers. second, I try bitmap(file=z.png) plot(1:10,main=a) dev.off() I can't get a chart with the right title =中文 Why have this difference? Encodings. bitmap(() uses postscript() and that is set up to use ISO-Latin1 on Unix. You can change it (see its help file) provided your version of gs has the fonts you need. It is almost certainly easier to use the png() device *if* you can plot the title you want on an x11() device. -- 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://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] ./configure needs /sw/lib?
On Sun, 29 Jun 2003, Tony Marlboro wrote: Hello, I am using R on Mac OS X. I have tried to install the package netCDF, but have run into a problem. The install.packages command fails during a call to the configure shell script in the package build directory, because it cannot find the netCDF libraries on my system. Those libraries are installed in /sw/lib, as they were installed with fink, and this system puts everything in /sw. Either I need a way to give configure flags to install.packages(), or this package is broken. Note that /sw/lib/R/etc/Makeconf has all the right build flags. Is there a mechanism for handling problems of this nature? Yes, to use R CMD INSTALL directly: use R CMD INSTALL --help to find out how. You need to supply --with-netCDF=/sw, I believe (but then the headers may not be found). It should be simpler to fix your OS: if you put /sw/include in your INCLUDE path and /sw/lib in your LIBRARY path then configure in netCDF should work `out of the box'. I would consider this to be a problem with your setup, not with R nor netCDF: why should netCDF know anything about fink? -- 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://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] Fitting inter-arrival time data
On Sun, 29 Jun 2003, M. Edward Borasky wrote: I have a collection of data which includes inter-arrival times of requests to a server. What I've done so far with it is use sm.density to explore the distribution, which found two large peaks. However, the peaks are made up of Gaussians, and that's not really correct, because the inter-arrival time can never be less than zero. In fact, the leftmost peak is centered at somewhere around ten seconds, and quite a bit of it extends into negative territory. What I'd like to do is fit this dataset to a mixture (sum) of exponentials, hyper-exponentials and hypo-exponentials. My preference is to use the well-known branching Erlang approximation (exponential stages) to the hyper- and hypo-exponentials. In this approximation, a distribution is specified by its mean and coefficient of variation. So far, what I've been able to come up with in a literature search has been something called the Expectation Maximization algorithm. And I haven't been able to locate R code for this. So my questions are: 1. Is EM the right way to go about this, or is there something better? Even for normal mixtures, direct likelihood maximization was considered to be better in several studies. The EM method converges notoriously slowly. 2. Is there some EM code in R that I could experiment with, or do I need to write my own? It's not an algorithm (despite its common name) so cannot be coding generically. There is EM code for normal mixtures in several places, e.g. in packages emclust and mda. Direct ML would be easier to code, I expect. 3. Is there a way this could be done using the existing R kernel density estimators and some kind of kernel that is zero for negative values of its argument? No, but there are ways to do by transforming the x scale. Local polynomial estimators (KernSmooth, locfit) will do better. For all of these see MASS (the book) and its on-line complements. -- 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://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] Returning contour co-ordinates
On 29-Jun-03 Paul Murrell wrote: There is a partial implementation of this available via a tiny R package (http://www.stat.auckland.ac.nz/~paul/R/clines_1.0.tar.gz) Excellent! Thanks. [...] This will become available via a call to contour() in the future. Even better! (Really tiny: I like that sort of program). Best wishes, Ted. E-Mail: (Ted Harding) [EMAIL PROTECTED] Fax-to-email: +44 (0)870 167 1972 Date: 30-Jun-03 Time: 08:35:12 -- XFMail -- __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] Fitting inter-arrival time data
On Monday 30 June 2003 01:23, M. Edward Borasky wrote: I have a collection of data which includes inter-arrival times of requests to a server. What I've done so far with it is use sm.density to explore the distribution, which found two large peaks. However, the peaks are made up of Gaussians, and that's not really correct, because the inter-arrival time can never be less than zero. In fact, the leftmost peak is centered at somewhere around ten seconds, and quite a bit of it extends into negative territory. if you data are positive, you could use sm.density(..., positive=TRUE) and possibly make use of the additional parameter delta for fine tuning best wishes, Adelchi Azzalini -- Adelchi Azzalini [EMAIL PROTECTED] Dipart.Scienze Statistiche, Università di Padova, Italia http://azzalini.stat.unipd.it/ __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
[R] R as COM client (rather than server)
Hello all Can R be used as a COM client (rather than as a COM server)? The following (Splus) code shows the sort of thing I'd like to do: pMIM - create.ole.object(mim31.Server) NoOutputLines - call.ole.method(pMIM, SendCmdLine, show w) for (i in 1:NoOutputLines) show(call.ole.method(pMIM, GetOutputLine)) release.ole.object(pMIM) I've tried to look at the RDCOM documentation but could not figure out whether this can be done. Regards David David Edwards, Biostatistics, Novo Nordisk A/S, Bagsværd, Denmark. [EMAIL PROTECTED] mailto:[EMAIL PROTECTED] Tlf: +45 44 42 62 35. Fax: +45 44 42 14 80 [[alternative HTML version deleted]] __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
[R] symbol size on a plot
Hi, I would like to get from a plot the size of the symbols plotted. Imagine I have the following plot function : plot(1:2,1:2, pch=15, cex=4) I would like the get the values SIZE1 and SIZE2 so that if I plot the following rectangle : rect(1.5,1.5, 1.5+SIZE1, 1.5+SIZE2) then the size of this square is exactely the same as the one of the symbols that have been plotted. Thanks for any idea. -- -- Philippe Hupé Institut Curie - Equipe Bioinformatique 26, rue d'Ulm - 75005 PARIS France +33 (0)1 42 34 65 29 [EMAIL PROTECTED] mailto:[EMAIL PROTECTED] __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
[R] Rmpi: send a function to a slave from master and let it run?
Hello All, Can send different functions to different slaves from master and let each slave run itself function using Rmpi? From the Rmpi version 0.4.2, I know how to send a function to all slaves and let slave run the function. mpi.send.Robj may send a function to a slave, but how let the salve run the function? Thanks. Lun __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] repeatedly applying function with matrix-rows as argument
apply(mymatrix, 1, function(x) myfun(x[1], x[2], x[3])) On Mon, 30 Jun 2003, Maarten Speekenbrink wrote: Suppose I have a function which takes three arguments. I would like to repeatedly apply the function, using a matrix N*3 in which each row supplies the three argements for the function. Is this possible? Thank you for your help in advance! -- 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://www.stat.math.ethz.ch/mailman/listinfo/r-help
[R] french map
Hello, I would like to know if (as the usa map with Splus), it is possible with R to plot the french map and to add points (representing towns for instance) on the figure in the appropriate (x,y) system. Thank you. Nathalie Peyrard __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
[R] R CMD check
when using R CMD check mypkg I get the error message ... * checking R files for library.dynam ... OK * checking generic/method consistency ... WARNING Error in .loadPackageQuietly(package, lib.loc) : Error in parse(file, n, text, prompt) : syntax error on line 95 Execution halted * checking for assignment functions with final arg not named 'value' ... WARNING Error in .loadPackageQuietly(package, lib.loc) : Error in parse(file, n, text, prompt) : syntax error on line 95 Execution halted ... What can I do to avoid this? I use R-1.7.0 on Linux RedHat. Any suggestions are appreciated. -- John Bjornar Bremnes Norwegian Meteorological Institute (met.no) Research and Development Department P.O.Box 43 Blindern, N-0313 Oslo, Norway Phone: (+47) 2296 3326. Fax: (+47) 2269 6355 __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] R as COM client (rather than server)
There is also the Omegahat collection of packages for DCOM which supports R as a client, user-definable server objects and event handlers. Together, RDCOMClient and RDCOMServer (and the SWinRegistry and SWinTypeLibs packages) provide a general way to handle arbitrary data types in R and COM. There is a description of how this differs from the S-Plus approach and Thomas' rdcom package. See http://www.omegahat.org/RDCOMClient Erich Neuwirth wrote: It can be done. But it is still in development and therefore not on CRAN. There is a library rcom which does exactly what you are asking for. http://sunsite.univie.ac.at/rcom/ always has the latest version of the R COM package, currently including the package for R as a client also. There is a special mailing list for questions related to R and (D)COM you can subscribe to it at http://mailman.csd.univie.ac.at/mailman/listinfo/rcom-l DED (David George Edwards) wrote: Hello all Can R be used as a COM client (rather than as a COM server)? The following (Splus) code shows the sort of thing I'd like to do: pMIM - create.ole.object(mim31.Server) NoOutputLines - call.ole.method(pMIM, SendCmdLine, show w) for (i in 1:NoOutputLines) show(call.ole.method(pMIM, GetOutputLine)) release.ole.object(pMIM) I've tried to look at the RDCOM documentation but could not figure out whether this can be done. Regards David David Edwards, Biostatistics, Novo Nordisk A/S, Bagsværd, Denmark. [EMAIL PROTECTED] mailto:[EMAIL PROTECTED] Tlf: +45 44 42 62 35. Fax: +45 44 42 14 80 [[alternative HTML version deleted]] __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help -- ___ Duncan Temple Lang[EMAIL PROTECTED] Bell Labs, Lucent Technologiesoffice: (908)582-3217 700 Mountain Avenue, Room 2C-259 fax:(908)582-3340 Murray Hill, NJ 07974-2070 http://cm.bell-labs.com/stat/duncan __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
RE: [R] R as COM client (rather than server)
Hi Duncan Thanks for the information, this looks very nice. Best regards David PS Some of the links on http://www.omegahat.org/RDCOMClient are broken. -Original Message- From: Duncan Temple Lang [mailto:[EMAIL PROTECTED] Sent: 30 June 2003 15:58 To: Erich Neuwirth Cc: DED (David George Edwards); '[EMAIL PROTECTED]' Subject: Re: [R] R as COM client (rather than server) There is also the Omegahat collection of packages for DCOM which supports R as a client, user-definable server objects and event handlers. Together, RDCOMClient and RDCOMServer (and the SWinRegistry and SWinTypeLibs packages) provide a general way to handle arbitrary data types in R and COM. There is a description of how this differs from the S-Plus approach and Thomas' rdcom package. See http://www.omegahat.org/RDCOMClient Erich Neuwirth wrote: It can be done. But it is still in development and therefore not on CRAN. There is a library rcom which does exactly what you are asking for. http://sunsite.univie.ac.at/rcom/ always has the latest version of the R COM package, currently including the package for R as a client also. There is a special mailing list for questions related to R and (D)COM you can subscribe to it at http://mailman.csd.univie.ac.at/mailman/listinfo/rcom-l DED (David George Edwards) wrote: Hello all Can R be used as a COM client (rather than as a COM server)? The following (Splus) code shows the sort of thing I'd like to do: pMIM - create.ole.object(mim31.Server) NoOutputLines - call.ole.method(pMIM, SendCmdLine, show w) for (i in 1:NoOutputLines) show(call.ole.method(pMIM, GetOutputLine)) release.ole.object(pMIM) I've tried to look at the RDCOM documentation but could not figure out whether this can be done. Regards David David Edwards, Biostatistics, Novo Nordisk A/S, Bagsværd, Denmark. [EMAIL PROTECTED] mailto:[EMAIL PROTECTED] Tlf: +45 44 42 62 35. Fax: +45 44 42 14 80 [[alternative HTML version deleted]] __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help -- ___ Duncan Temple Lang[EMAIL PROTECTED] Bell Labs, Lucent Technologiesoffice: (908)582-3217 700 Mountain Avenue, Room 2C-259 fax:(908)582-3340 Murray Hill, NJ 07974-2070 http://cm.bell-labs.com/stat/duncan __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] ./configure needs /sw/lib?
On Mon, 30 Jun 2003, Tony Marlboro wrote: Thank you for your reply, Professor Ripley. Yes, to use R CMD INSTALL directly: use R CMD INSTALL --help to find out how. You need to supply --with-netCDF=/sw, I believe (but then the headers may not be found). R CMD INSTALL --configure-args=--with-netCDF=/sw netCDF_1.5.tar.gz was the correct incantation, thanks. I spent a considerable amount of time trying to figure this out on my own, and I think it would have been easier if the Add-on packages section of the R Installation manual were more complete. It would be nice to highlight the differences between install.packages() and R CMD INSTALL, if at least to mention the extra capabilities of R CMD INSTALL. I would like to submit a documentation patch. With whom should I correspond? It's in the FAQ. Of course, it would be nice for the rest of us if MacOS X were not so out-of-kilter. It should be simpler to fix your OS: if you put /sw/include in your INCLUDE path and /sw/lib in your LIBRARY path then configure in netCDF should work `out of the box'. Are you referring to environment variables called INCLUDE and LIBRARY? I tried setting them, then running R CMD INSTALL without any extra args to configure, and it failed. I'm quite curious what you mean by INCLUDE path and LIBRARY path. On a normal Unix system, something like C_INCLUDE_PATH and LD_LIBRARY_PATH, who knows on such a system as MacOS X. -- 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://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] french map
Peyrard Nathalie wrote: I would like to know if (as the usa map with Splus), it is possible with R to plot the french map and to add points (representing towns for instance) on the figure in the appropriate (x,y) system. You can use my Rmap library (http://www.maths.lancs.ac.uk/Software/Rmap/) to plot geographic maps in R. You then need to get the data for France. Rmap is tested mostly with ESRI shapefile datasets. Here are two web sites with French department data sets, but you must make sure your use of them conforms with the licensing of the data set: http://www.cdc.gov/epiinfo/EIeurope.htm http://www.ign.fr/affiche_rubrique.asp?rbr_id=809lng_id=FR Rmap is in very early stages of development, and so you may have problems getting it working on your machine. It is mainly tested on Linux platforms, so Windows users may have problems. Barry Rowlingson Maths and Stats Lancaster University Lancaster, UK __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
[R] Your Message to Bonzi.com has an Attachment [T2003063000K3]
=== IMPORTANT! The message that you have sent to BONZI Software has a file attached to it. Due to the high level of virus messages we are currently receiving, your message has been discarded. Please reply to this message, make sure that there are no attachments to the message, and re-state your question. Any message that arrives with no attachments will receive a response. BonziMAIL messages include attachments and are not accepted by our mail system. Please open your regular e-mail program and write us a message using only plain text. You will not be able to send us messages in HTML format with background or foreground images attached to them. Send your messages as plain or rich text only. IncrediMail users... With a new message open, you must go to your Message menu and click on Plain Text before sending your message. Any regular message using IncrediMail will contain attachments and cause your message to be discarded, so you must convert your support message to plain text only before you send it. Thank you for your cooperation. Customer Service BONZI Software === __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] ./configure needs /sw/lib?
Thank you for your reply, Professor Ripley. Yes, to use R CMD INSTALL directly: use R CMD INSTALL --help to find out how. You need to supply --with-netCDF=/sw, I believe (but then the headers may not be found). R CMD INSTALL --configure-args=--with-netCDF=/sw netCDF_1.5.tar.gz was the correct incantation, thanks. I spent a considerable amount of time trying to figure this out on my own, and I think it would have been easier if the Add-on packages section of the R Installation manual were more complete. It would be nice to highlight the differences between install.packages() and R CMD INSTALL, if at least to mention the extra capabilities of R CMD INSTALL. I would like to submit a documentation patch. With whom should I correspond? It should be simpler to fix your OS: if you put /sw/include in your INCLUDE path and /sw/lib in your LIBRARY path then configure in netCDF should work `out of the box'. Are you referring to environment variables called INCLUDE and LIBRARY? I tried setting them, then running R CMD INSTALL without any extra args to configure, and it failed. I'm quite curious what you mean by INCLUDE path and LIBRARY path. Regards, Tony __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] french map
Have you tried www.r-project.org - search - R Site Search? There are several geographers who follow this list. From the above mentioned search, I found an exchange with subject Mapping in R discussing such a thing dated mercredi 21 novembre 2001 17:21, from: Christophe DECLERCQ, MD Observatoire Régional de la Santé Nord-Pas-de-Calais 13, rue Faidherbe 59046 LILLE Cedex FRANCE Phone +33 3 20 15 49 24 Fax +33 3 20 55 92 30 E-mail [EMAIL PROTECTED] hope this helps. spencer graves Peyrard Nathalie wrote: Hello, I would like to know if (as the usa map with Splus), it is possible with R to plot the french map and to add points (representing towns for instance) on the figure in the appropriate (x,y) system. Thank you. Nathalie Peyrard __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] R CMD check
You have an error in the R files of your package. Before you even do R CMD check, do try loading the package in R. On Mon, 30 Jun 2003, John Bjørnar Bremnes wrote: when using R CMD check mypkg I get the error message ... * checking R files for library.dynam ... OK * checking generic/method consistency ... WARNING Error in .loadPackageQuietly(package, lib.loc) : Error in parse(file, n, text, prompt) : syntax error on line 95 Execution halted * checking for assignment functions with final arg not named 'value' ... WARNING Error in .loadPackageQuietly(package, lib.loc) : Error in parse(file, n, text, prompt) : syntax error on line 95 Execution halted ... What can I do to avoid this? I use R-1.7.0 on Linux RedHat. Any suggestions are appreciated. -- 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://www.stat.math.ethz.ch/mailman/listinfo/r-help
[R] spatial correlation test
hello,
I want to do a test for spatial correlation.
I tried it with geary.test() but I don't understand the required input.
x= a numeric vector the same length as the neighbours list in listw (my
sampled data, I assume)
listw= a listw object created for example by nb2listw (well when I check
nb2listw() I get to neighbours - an object of class nb - but I couldn't
figure out, what nb is or how I create such a class
with sp.mantel.mc {spdep} I have the same problem: listw created by nb2listw
isn't there a more straight forward method ;-) to check for spatial
correlation? like x and y coordinates plus my sampled data?
thanks, Martin
BTW thanks everybody for their help with my last problem - [R] regression for
several responses - it worked perfectly
__
[EMAIL PROTECTED] mailing list
https://www.stat.math.ethz.ch/mailman/listinfo/r-help
[R] if else statements in R
Hi, there
I am a grad student struggling to get my syntax right in a model I am
building in R.
I am trying to specify a variable,W, in a loop, such that on the first
iteration, it is equal to Wo, my starting value, which I have already
specified with
Wo-9.2
On any other iteration other than the first, I want W to equal the
previous value of W in the iteration. plus an increment from that previous
iteration, divided by another value. This then becomes the value used in
all calculations in the iteration at hand.
Here is my code, that does not work:
W- function(w)
{
if (comp[i,1]=1) W[i]-Wo else
W[i]-(work[i-1,5]work[i-1,13]*/Ef)
}
work is the dataframe that I am rbinding my interations into, and the W
variable is the 5th variable in that frame, and the additive to W is the
13th variable in that frame.
However, this is where the program stalls on me:
{
+
+ W- function(w)
+ {
+ if (comp[i,1]=1) W[i]-Wo else
Error: syntax error
Execution halted
I've also attempted this variation;
W- function(w)
if (comp[i,1]=1) {W[i]-Wo} else
W[i]-(work[i-1,5]work[i-1,13]*/Ef)
Which meets with an equal lack of success, and stalls in the same spot as
the previous version.
Does anyone have any hints on how to make this if else statement work to do
what I need? This is my first time trying to use these statements, and the
S-plus manual i have is proving to be terribly unhelpful.
What am I doing wrong?
Mike
Michael Rennie
M.Sc. Candidate
University of Toronto at Mississauga
3359 Mississauga Rd. N.
Mississauga, ON L5L 1C6
Ph: 905-828-5452 Fax: 905-828-3792
[[alternative HTML version deleted]]
__
[EMAIL PROTECTED] mailing list
https://www.stat.math.ethz.ch/mailman/listinfo/r-help
[R] sample from a list of names for random groups
Dear R-users, I need to sample from a list of names (people) and create 2 random groups with unique item. Sure sample() function is a good point to start but I can't find example to solve my work. any tips? example? Thank -- Daniele Medri __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
[R] if else statements in R
Hi, there
I am a grad student struggling to get my syntax right in a model I am
building in R.
I am trying to specify a variable,W, in a loop, such that on the first
iteration, it is equal to Wo, my starting value, which I have already
specified with
Wo-9.2
On any other iteration other than the first, I want W to equal the
previous value of W in the iteration. plus an increment from that previous
iteration, divided by another value. This then becomes the value used in
all calculations in the iteration at hand.
Here is my code, that does not work:
W- function(w)
{
if (comp[i,1]=1) W[i]-Wo else
W[i]-(work[i-1,5]work[i-1,13]*/Ef)
}
work is the dataframe that I am rbinding my interations into, and the W
variable is the 5th variable in that frame, and the additive to W is the
13th variable in that frame.
However, this is where the program stalls on me:
{
+
+ W- function(w)
+ {
+ if (comp[i,1]=1) W[i]-Wo else
Error: syntax error
Execution halted
I've also attempted this variation;
W- function(w)
if (comp[i,1]=1) {W[i]-Wo} else
W[i]-(work[i-1,5]work[i-1,13]*/Ef)
Which meets with an equal lack of success, and stalls in the same spot as
the previous version.
Does anyone have any hints on how to make this if else statement work to do
what I need? This is my first time trying to use these statements, and the
S-plus manual i have is proving to be terribly unhelpful.
What am I doing wrong?
Mike
Michael Rennie
M.Sc. Candidate
University of Toronto at Mississauga
3359 Mississauga Rd. N.
Mississauga, ON L5L 1C6
Ph: 905-828-5452 Fax: 905-828-3792
[[alternative HTML version deleted]]
__
[EMAIL PROTECTED] mailing list
https://www.stat.math.ethz.ch/mailman/listinfo/r-help
[R] Novice Questions
I'm writing a program to perform linear regressions to estimate the number of bank teller transactions per hour of various types based upon day of week, time of day, week of month and several prices. I've got about 25,000 records in my dataset, 85 columns of transaction counts (used 1 at a time), about 50 columns of binary indicators (day, week, pay period, hour, branch), and a half dozen real valued prices. My program hangs on some regressions as I add interactions, probably due to logic problems in my code or collinearity problems in the data. 1) I'm running my program via the source() command. It appears that source() does not print any messages until it completes. Is there a way to get diagnostic messages to print immediately rather than when the source() command has completed? 2) I'm fairly certain that I've got some collinearity in the data set and the interactions. I've found an append (Ott Toomet 5/30/2003) that talks about a procedure to find collinearity problems using model.matrix() to generate the dataset with interactions and kappa() to determine the condition number of the matrix. Is there a more automated way to find collinear variables? 3) Is there a way to get lm() and/or step() or some other package to give a model with only coefficients that are significant at a particular level? 4) Is there a way to suppress display of a password when using the RODBC odbcConnect() function, or to get the function to prompt for a password? 5) What is the practical size limit on the number of terms in model? I know that I won't be able to consider all interactions, but would like to have some idea when to give up and go with what I've got. = Bruce Moore __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] if else statements in R
On Mon, Jun 30, 2003 at 11:21:52AM -0400, Michael Rennie wrote:
W- function(w)
{
if (comp[i,1]=1) W[i]-Wo else
== is comparison operator, but = is assignment one.
This code also doesn't work:
x - 0
if (x = 1)
Error: syntax error
But this works:
if (x == 1)
+
Chack also help(==), help(=)
--
WBR,
Timur.
__
[EMAIL PROTECTED] mailing list
https://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] NLME Covariates
Harold Doran [EMAIL PROTECTED] writes: In HLM, one can specify a covariate at one of the levels. For example, if the data structure are repeated observations nested within students nested within schools, school size might be a covariate that is used at level 3, but not at the other levels. In HLM this is rather easy to do. However, how can one specify a covariate in R for only one of the levels? I have a sample data set with the structure as described above. I fit the unconditional model in R as model1-lme(math~year, random=~year|schoolid/childid, data=datafile) Now, if I want to enter female as a covariate at level 2 only, how might I modify the code to accomplish this? There is no distinction between level 1 and level 2 variables in the fixed-effects part of an lme model. Once the data are organized in a composite table (i.e. one table that includes the value of each covariate for each observation) one simply writes a linear model expression for the fixed effects. You need to incorporate the female indicator into your 'datafile' data frame. The merge function is a good way to do this (I had forgotten about the merge function when we spoke about this a few weeks ago). After that you could fit a model using, say, model2 - lme(math ~ year * female, random=~year|schoolid/childid, data = datafile) -- Douglas Bates[EMAIL PROTECTED] Statistics Department608/262-2598 University of Wisconsin - Madisonhttp://www.stat.wisc.edu/~bates/ __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] if else statements in R
This is untested, so try it first, but my approach would be:
W- function(w)
{
W[i]-ifelse(comp[i,1]==1, Wo, (work[i-1,5]work[i-1,13]*/Ef))
}
Best,
Andy Perrin
--
Andrew J Perrin - http://www.unc.edu/~aperrin
Assistant Professor of Sociology, U of North Carolina, Chapel Hill
[EMAIL PROTECTED] * andrew_perrin (at) unc.edu
On Mon, 30 Jun 2003, Michael Rennie wrote:
Hi, there
I am a grad student struggling to get my syntax right in a model I am
building in R.
I am trying to specify a variable,W, in a loop, such that on the first
iteration, it is equal to Wo, my starting value, which I have already
specified with
Wo-9.2
On any other iteration other than the first, I want W to equal the
previous value of W in the iteration. plus an increment from that previous
iteration, divided by another value. This then becomes the value used in
all calculations in the iteration at hand.
Here is my code, that does not work:
W- function(w)
{
if (comp[i,1]=1) W[i]-Wo else
W[i]-(work[i-1,5]work[i-1,13]*/Ef)
}
work is the dataframe that I am rbinding my interations into, and the W
variable is the 5th variable in that frame, and the additive to W is the
13th variable in that frame.
However, this is where the program stalls on me:
{
+
+ W- function(w)
+ {
+ if (comp[i,1]=1) W[i]-Wo else
Error: syntax error
Execution halted
I've also attempted this variation;
W- function(w)
if (comp[i,1]=1) {W[i]-Wo} else
W[i]-(work[i-1,5]work[i-1,13]*/Ef)
Which meets with an equal lack of success, and stalls in the same spot as
the previous version.
Does anyone have any hints on how to make this if else statement work to do
what I need? This is my first time trying to use these statements, and the
S-plus manual i have is proving to be terribly unhelpful.
What am I doing wrong?
Mike
Michael Rennie
M.Sc. Candidate
University of Toronto at Mississauga
3359 Mississauga Rd. N.
Mississauga, ON L5L 1C6
Ph: 905-828-5452 Fax: 905-828-3792
[[alternative HTML version deleted]]
__
[EMAIL PROTECTED] mailing list
https://www.stat.math.ethz.ch/mailman/listinfo/r-help
__
[EMAIL PROTECTED] mailing list
https://www.stat.math.ethz.ch/mailman/listinfo/r-help
RE: [R] french map
Nathalie, You could have a look at the web site of the Institut Géographique National (http://www.ign.fr) where you can download a free SHAPEFILE with polygon data for the French départements. You can choose one of two projections: LAMBERT II étendu or LAMBERT 93 (http://www.ign.fr/affiche_rubrique.asp?rbr_id=810lng_id=FR). In the associated DBF file, you get the name and the x,y coordinates for the préfecture of each département. You could use these data in R with one of the packages which read shapefiles (for example, 'shapefiles' which is on CRAN or the draft package 'maptools'- see http://spatial.nhh.no/R/ - which is already very useful as it is). I hope it helps. Christophe -- Christophe DECLERCQ, MD Observatoire Régional de la Santé Nord-Pas-de-Calais 13, rue Faidherbe 59046 LILLE Cedex FRANCE Phone +33 3 20 15 49 24 Fax +33 3 20 55 92 30 E-mail [EMAIL PROTECTED] -Message d'origine- De : [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] la part de Peyrard Nathalie Envoyé : lundi 30 juin 2003 15:21 À : [EMAIL PROTECTED] Objet : [R] french map Hello, I would like to know if (as the usa map with Splus), it is possible with R to plot the french map and to add points (representing towns for instance) on the figure in the appropriate (x,y) system. Thank you. Nathalie Peyrard __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] spatial correlation test
At 18:48 30/06/2003, Martin Wegmann wrote:
hello,
I want to do a test for spatial correlation.
I tried it with geary.test() but I don't understand the required input.
x= a numeric vector the same length as the neighbours list in listw (my
sampled data, I assume)
listw= a listw object created for example by nb2listw (well when I check
nb2listw() I get to neighbours - an object of class nb - but I couldn't
figure out, what nb is or how I create such a class
with sp.mantel.mc {spdep} I have the same problem: listw created by nb2listw
isn't there a more straight forward method ;-) to check for spatial
correlation? like x and y coordinates plus my sampled data?
This functions require a list of spatial weights for each geographical
unit. To construct this list, you must firstly establish the neighborhood
relationships (who are the neighbors of a point). There are different ways
to construct this neighborhood: based on distances (dnearneigh), number of
nearest neighbors (knearneigh)... Then, you must transform this
neighborhood to weights (see nb2listw for example). Here is a small example
requiring the tripack library based on tesselation and voronoi mosaic to
create the neighboorhood:
xy=matrix(rnorm(20),5,2)
z=rnorm(5)
library(spdep)
mynb=tri2nb(xy)
mylw=nb2listw(mynb)
geary.mc(z,mylw,10)
Monte-Carlo simulation of Geary's C
data: z
weights: mylw
number of simulations + 1: 11
There is no simplest method.
statistic = 0.8384, observed rank = 2, p-value = 0.1818
alternative hypothesis: less
__
[EMAIL PROTECTED] mailing list
https://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] within group variance of the coeficients in LME
J.R. Lockwood [EMAIL PROTECTED] writes: Dear listers, I can't find the variance or se of the coefficients in a multilevel model using lme. The component of an lme() object called apVar provides the estimated asymptotic covariance matrix of a particular transformation of the variance components. Dr. Bates can correct me if I'm wrong but I believe it is the matrix logarithm of Cholesky decomposition of the covariance matrix of the random effects. I believe the details are in the book by Pinheiro and Bates. Once you know the transformation you can use the apVar elements to get estimated asympotic standard errors for your variance components estimates using the delta method. J.R. Lockwood 412-683-2300 x4941 [EMAIL PROTECTED] http://www.rand.org/methodology/stat/members/lockwood/ First, thanks to those who answered the question. I have been away from my email for about a week and am just now catching up on the r-help list. As I understand the original question from Andrej he wants to obtain the standard errors for coefficients in the fixed effects part of the model. Those are calculated in the summary method for lme objects and returned as the component called 'tTable'. Try library(nlme) example(lme) summary(fm2)$tTable to see the raw values. Other software for fitting mixed-effects models, such as SAS PROC MIXED and HLM, return standard errors along with the estimates of the variances and covariances of the random effects. We don't return standard errors of estimated variances because we don't think they are useful. A standard error for a parameter estimate is most useful when the distribution of the estimator is approximately symmetric, and these are not. Instead we feel that the variances and covariances should be converted to an unconstrained scale, and preferably a scale for which the log-likelihood is approximately quadratic. The apVar component that you mention is an approximate variance-covariance matrix of the variance components on an unbounded parameterization that uses the logarithm of any standard deviation and Fisher's z transformation of any correlations. If all variance-covariance matrices being estimated are 1x1 or 2x2 then this parameterization is both unbounded and unconstrained. If any are 3x3 or larger then this parameterization must be further constrained to ensure positive definiteness. Nevertheless, once we have finished the optimization we convert to this 'natural' parameterization to assess the variability of the estimates because these parameters are easily interpreted. The actual optimization of the profiled log-likelihood is done using the log-Cholesky parameterization that you mentioned because it is always unbounded and unconstrained. Interpreting elements of this parameter vector is complicated. I hope this isn't too confusing. __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
[R] Seemingly unrelated regressions
Is there an implementation of SUR in R? These are used commonly in economics. Thanks -- Richard A. Hinrichsen __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] sample from a list of names for random groups
n1 - 2 n2 - 3 (S - sample(letters, n1+n2)) [1] f a d n l (S1 - sample(S, n1)) [1] l n (S2 - S[!is.element(S, S1)]) [1] f a d hope this helps. spencer graves Daniele Medri wrote: Dear R-users, I need to sample from a list of names (people) and create 2 random groups with unique item. Sure sample() function is a good point to start but I can't find example to solve my work. any tips? example? Thank __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] if else statements in R
On 30 Jun 2003 at 11:24, Michael Rennie wrote:
Hola!
Hi, there
I am a grad student struggling to get my syntax right in a model I am
building in R.
I am trying to specify a variable,W, in a loop, such that on the first
iteration, it is equal to Wo, my starting value, which I have already
specified with
Wo-9.2
On any other iteration other than the first, I want W to equal the
previous value of W in the iteration. plus an increment from that previous
iteration, divided by another value. This then becomes the value used in
all calculations in the iteration at hand.
Here is my code, that does not work:
There are multiple problems with this code
1) You use W as a name of a function AND as a name of an array
inside that function. Might not be a syntax error (?), but is asking
for problems. Use an other name for your array, and assign it first.
2) The variable i is not given a value anywhere in your code.
3)The condition in the if statement uses = and not ==, = is
assignment, == is test lfor equality. Actuallt, your comp[i,1] gets
assigned 1, that is also the value of the assignment, and in the
logical test the 1 will be interpreted as TRUE, so you will never get
the else branch!
W- function(w)
{
if (comp[i,1]=1) W[i]-Wo else
W[i]-(work[i-1,5]work[i-1,13]*/Ef)
}
Maybe youwant something like:
W - function(w) {
result - numeric(length=?)
if (comp[i,1]==1) result[i] - W0 else
result[i] - work[i-1,5] * work[i-1,13]/Ef
}
but it is really impossible to tell, as your function are using
global variables. Another good idea is to avoid global variables.
Kjetil Halvorsen
work is the dataframe that I am rbinding my interations into, and the W
variable is the 5th variable in that frame, and the additive to W is the
13th variable in that frame.
However, this is where the program stalls on me:
{
+
+ W- function(w)
+ {
+ if (comp[i,1]=1) W[i]-Wo else
Error: syntax error
Execution halted
I've also attempted this variation;
W- function(w)
if (comp[i,1]=1) {W[i]-Wo} else
W[i]-(work[i-1,5]work[i-1,13]*/Ef)
Which meets with an equal lack of success, and stalls in the same spot as
the previous version.
Does anyone have any hints on how to make this if else statement work to do
what I need? This is my first time trying to use these statements, and the
S-plus manual i have is proving to be terribly unhelpful.
What am I doing wrong?
Mike
Michael Rennie
M.Sc. Candidate
University of Toronto at Mississauga
3359 Mississauga Rd. N.
Mississauga, ON L5L 1C6
Ph: 905-828-5452 Fax: 905-828-3792
[[alternative HTML version deleted]]
__
[EMAIL PROTECTED] mailing list
https://www.stat.math.ethz.ch/mailman/listinfo/r-help
__
[EMAIL PROTECTED] mailing list
https://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] degrees of freedom in a LME model
Federico Calboli [EMAIL PROTECTED] writes: Dear All, I am analysing some data for a colleague (not my data, gotta be published so I cannot divulge). My response variable is the number of matings observed per day for some fruitlies. My factors are: Day: the observations were taken on 9 days Regime: 3 selection regimes Line: 3 replicates per selection regime. I have 81 observations in total The lines are coded A to I, so I do not need to do any extra grouping. my model is: anova(lme(Matings ~ Day * Regime, random = ~1| Line/Day, mydata)) I would expect to have: 1 df per Day 2 df per Regime 2 df per Day * Regime 6 df per Line %in% Regime 6 df per Day * Line %in% Regime, so my anova would have: numDF denDF int 1 63 Day 1 6 Regime2 6 D*R 2 6 what I get is: numDF denDF int 1 69 Day 1 69 Regime2 6 D*R 2 69 why is lme not calculating correctly the Line/Day interation ? I think your calculation is based on using only within-strata information whereas lme uses both within-strata and between-strata information for estimates of effects. The way that we calculate denominator degrees of freedom is described on pp. 90-91 of Pinheiro and Bates (2000). For each term in the fixed-effects we determine the innermost level of the random effects at which is it changing. Because Regime is constant for each Line it has the fewest degrees of freedom but Day is changing within Line so terms in Day have more degrees of freedom. Is this what you intended? I must admit I am having difficulty understanding the structure of the experiment but it is still Monday morning for me so perhaps that is not surprising. I am using R 1.7.0 under W2K, although I updated the packages and I get the warning nlme lib built under R1.7.1... Regards, Federico -- Douglas Bates[EMAIL PROTECTED] Statistics Department608/262-2598 University of Wisconsin - Madisonhttp://www.stat.wisc.edu/~bates/ __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
[R] make 1.7.1 crashes in Mac OS X
I trying to compile R-.1.7.1 under OS X. Configure worked fine; then make crashes with: /sw/lib/libg2c.a(err.o) definition of common _f__formatted (size 4) /sw/lib/libg2c.a(err.o) definition of common _f__hiwater (size 4) /sw/lib/libg2c.a(err.o) definition of common _f__putn (size 4) /sw/lib/libg2c.a(err.o) definition of common _f__reading (size 4) /sw/lib/libg2c.a(err.o) definition of common _f__recpos (size 4) /sw/lib/libg2c.a(err.o) definition of common _f__sequential (size 4) /sw/lib/libg2c.a(err.o) definition of common _f__getn (size 4) /sw/lib/libg2c.a(err.o) definition of common _f__icptr (size 4) /sw/lib/libg2c.a(err.o) definition of common f(short, void, int, char) (size 4) /usr/bin/libtool: internal link edit command failed make[4]: *** [libRlapack.dylib] Error 1 make[3]: *** [R] Error 2 make[2]: *** [R] Error 1 make[1]: *** [R] Error 1 make: *** [R] Error 1 [beethoven:~/INSTALL/R-1.7.1] herron% Any ideas here? Thanks, michael __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] make 1.7.1 crashes in Mac OS X
This is described in the MacOS X section of the R-admin manual. The file INSTALL does ask you to read it: please don't expect R-help readers to do so for you. On Mon, 30 Jun 2003, Michael Herron wrote: I trying to compile R-.1.7.1 under OS X. Configure worked fine; then make crashes with: /sw/lib/libg2c.a(err.o) definition of common _f__formatted (size 4) /sw/lib/libg2c.a(err.o) definition of common _f__hiwater (size 4) /sw/lib/libg2c.a(err.o) definition of common _f__putn (size 4) /sw/lib/libg2c.a(err.o) definition of common _f__reading (size 4) /sw/lib/libg2c.a(err.o) definition of common _f__recpos (size 4) /sw/lib/libg2c.a(err.o) definition of common _f__sequential (size 4) /sw/lib/libg2c.a(err.o) definition of common _f__getn (size 4) /sw/lib/libg2c.a(err.o) definition of common _f__icptr (size 4) /sw/lib/libg2c.a(err.o) definition of common f(short, void, int, char) (size 4) /usr/bin/libtool: internal link edit command failed make[4]: *** [libRlapack.dylib] Error 1 make[3]: *** [R] Error 2 make[2]: *** [R] Error 1 make[1]: *** [R] Error 1 make: *** [R] Error 1 [beethoven:~/INSTALL/R-1.7.1] herron% Any ideas here? Thanks, michael __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help -- 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://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] dropping factor levels in subset
Adaikalavan Ramasamy [EMAIL PROTECTED] writes: Another option is pruneLevels() in library nlme. x - factor( c( 0,1,2,1,2 ) ) x [1] 0 1 2 1 2 Levels: 0 1 2 pruneLevels( x[-1] ) [1] 1 2 1 2 Levels: 1 2 That function has been removed from the latest release of the nlme package because it not needed. All uses of pruneLevels in nlme were replaced by code of the form myfactor[] = myfactor[, drop = TRUE] __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] spatial correlation test
On Monday 30 June 2003 15:23, Barry Rowlingson wrote: Think you may be looking at the wrong sort of spatial correlation! For Geary tests you are comparing 'adjacent' objects, where adjacency is defined however you want - N-nearest neighbours, shared border between regions etc etc. sorry, I misunderstood the purpose of geary's I test, thanks for this info. When you say 'sampled data' it sounds more like you've got samples taken at locations, and you want to investigate spatial correlation as a function of distance between samples? Am I guessing right? Yes you are right. I want to look for spatial correlation of my samples as a function of distances between sampling sites (x,y coords). Take a look at some of the R kriging libraries, which will have functions to plot variograms. This is a plot of something like E(|Y_i - Y_j|) against distance. Baz I found variograms() and correlograms(), but is there a way to get the a p-value for spatial correlation? additionaly I found sp.correlogram() but again with this mysterious nb class. thanks, martin __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
[R] pairs and points
Hi, I am plotting a matrix/data frame with 10 variables by pairs. Is it possible to add another 10-dimensional point afterwards by something like points does for two-dimensional plots? Best, Christian -- *** Christian Hennig Seminar fuer Statistik, ETH-Zentrum (LEO), CH-8092 Zuerich (currently) and Fachbereich Mathematik-SPST/ZMS, Universitaet Hamburg [EMAIL PROTECTED], http://stat.ethz.ch/~hennig/ [EMAIL PROTECTED], http://www.math.uni-hamburg.de/home/hennig/ ### ich empfehle www.boag.de __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] degrees of freedom in a LME model
Dear Prof. Bates, Thank you for your reply. I did actually check the book at pages 89-92, but I have to say I found it a bit cryptic, if not downright confusing, for a genetist like me. Any day of the week. To use the example in the book, I cannot see why MACHINE is inner to WORKER. Or where the Pi = sum of df for the term estimatet at level i... To me it's just a two way anova with one random effect + one interaction. My df correspond to those in the book, but I calculated them in the bog standard way of 2 df for 3 machines, 5 df for 6 workers and 2 * 5 = 10 df for the interaction...oh well... I attach the datasest (I did a sample with replace = TRUE, should have thought of this earlier...). I hope thing would be clearer. It is obvious that if I consider day a factor, as I have just one datapoint per day per line within regime, I end up using all my degrees of freedom: 2 df for 3 regimes 6 df for line within regime 8 df for day (9 days, day as factor) 16 df for regime * day 48 df for line * day total 80 df, with 0 df remaining for the error. A bit of a problem I daresay, but I did not collect the data! BUT I did calculate my anova considering day as a continuous variable, 2 df for 3 regimes 6 df for line within regime 1 df for day (day as a number) 2 df for regime * day 6 df for line * day total 17 df, with 63 df remaining for the error. I still do not get why the interaction term Regime*Day is not tested on the interaction Line-in-regime*Day... In my analysis LME is clumping Error and Line-in-regime*Day together, judging by the df I was talking about in my previuos email. To me it should be just another bog standard situation...But if I were smart enough to be a statistician I would not be here doing genetics ;) Regards, Federico Calboli Day LineRegime Matings 2 501 es 0.4 4 501 es 0.32989691 9 501 es 0.48484848 11 501 es 0.72727273 16 501 es 0.34042553 18 501 es 0.56470588 25 501 es 0.37509377 30 501 es 0. 32 501 es 0.7778 2 502 es 0.57142857 4 502 es 1.0667 9 502 es 0.16 11 502 es 0.4 16 502 es 0.4 18 502 es 0. 25 502 es 0.80808081 30 502 es 0.48 32 502 es 0.25531915 2 503 es 0 4 503 es 0.72727273 9 503 es 0.3 11 503 es 0.7778 16 503 es 0.34042553 18 503 es 1.0667 25 503 es 0.32989691 30 503 es 1.2444 32 503 es 0.19153725 2 fb1 fb 0.72727273 4 fb1 fb 0.42105263 9 fb1 fb 0.32989691 11 fb1 fb 0.32323232 16 fb1 fb 0.37509377 18 fb1 fb 0.51612903 25 fb1 fb 0.4 30 fb1 fb 0.24742268 32 fb1 fb 0.24742268 2 fb2 fb 1. 4 fb2 fb 0.25263158 9 fb2 fb 0.6667 11 fb2 fb 1.0667 16 fb2 fb 0.97959184 18 fb2 fb 0.42105263 25 fb2 fb 0.57142857 30 fb2 fb 1.1556 32 fb2 fb 0.80808081 2 fb3 fb 0.18952106 4 fb3 fb 0.6667 9 fb3 fb 1.22033898 11 fb3 fb 0.35955056 16 fb3 fb 1.68421053 18 fb3 fb 0.57461174 25 fb3 fb 0.93506493 30 fb3 fb 0.80808081 32 fb3 fb 0.57461174 2 mb1 mb 0. 4 mb1 mb 0.3902439 9 mb1 mb 0.42105263 11 mb1 mb 0.48484848 16 mb1 mb 0.5556 18 mb1 mb 1.68421053 25 mb1 mb 0.4 30 mb1 mb 0.16 32 mb1 mb 0.09523809 2 mb2 mb 0.7778 4 mb2 mb 0.68817204 9 mb2 mb 0.25263158 11 mb2 mb 1. 16 mb2 mb 0.5 18 mb2 mb 0.37509377 25 mb2 mb 0.16494845 30 mb2 mb 2.46153846 32 mb2 mb 0.47058824 2 mb3 mb 1.0667 4 mb3 mb 0.5 9 mb3 mb 0.5 11 mb3 mb 0.38095238 16 mb3 mb 0.26373626 18 mb3 mb 0.87912088 25 mb3 mb 0.5556 30 mb3 mb 0.74418605 32 mb3 mb 1. I think your calculation is based on using only within-strata information whereas lme uses both within-strata and between-strata information for estimates of effects. The way that we calculate denominator degrees of freedom is described on pp. 90-91 of Pinheiro and Bates (2000). For each term in the fixed-effects we determine the innermost level of the random effects at which is it changing. Because Regime is constant for each
Re: [R] spatial correlation test
(I think Barry Rowlingson replied off-list, both his advice and Stéphane Dray's reply are relevant) On Mon, 30 Jun 2003, Martin Wegmann wrote: On Monday 30 June 2003 15:23, Barry Rowlingson wrote: Think you may be looking at the wrong sort of spatial correlation! For Geary tests you are comparing 'adjacent' objects, where adjacency is defined however you want - N-nearest neighbours, shared border between regions etc etc. sorry, I misunderstood the purpose of geary's I test, thanks for this info. When you say 'sampled data' it sounds more like you've got samples taken at locations, and you want to investigate spatial correlation as a function of distance between samples? Am I guessing right? Yes you are right. I want to look for spatial correlation of my samples as a function of distances between sampling sites (x,y coords). Take a look at some of the R kriging libraries, which will have functions to plot variograms. This is a plot of something like E(|Y_i - Y_j|) against distance. Baz I found variograms() and correlograms(), but is there a way to get the a p-value for spatial correlation? additionaly I found sp.correlogram() but again with this mysterious nb class. There is a literature that you will find referenced on help pages of the functions that you are interested in. For geary.test(), the reference is: Cliff, A. D., Ord, J. K. 1981 Spatial processes, Pion, p. 21. For sp.correlogram(): Cliff, A. D., Ord, J. K. 1981 Spatial processes, Pion, pp. 118-122, Martin, R. L., Oeppen, J. E. 1975 The identification of regional forecasting models using space-time correlation functions, Transactions of the Institute of British Geographers, 66, 95-118. These are the places to look first. For nb2listw() - Tiefelsdorf, M., Griffith, D. A., Boots, B. 1999 A variance-stabilizing coding scheme for spatial link matrices, Environment and Planning A, 31, pp. 165-180. The nb class defines neighbour relations needed to carry out further calculations, and is a list of integer vectors containing neighbour region number ids, quoting its documentation in the example Stéphane Dray used, tri2nb() to generate neighbours from points by triangulation. If your point data are not areal but are sampled from a possibly continuous surface, then, as Barry Rowlingson suggested, you could look at one or other of the geostatistical packages, for example sgeostat. However, asking for a p-value implies that you are testing some kind of a hypothesis, doesn't it? It is possible to do Moran tests within a testing framework in sp.correlogram(), and indeed to provide nb2listw() with inverse distance weights, but it isn't clear that this would answer your underlying research question. Roger -- Roger Bivand Economic Geography Section, Department of Economics, Norwegian School of Economics and Business Administration, Breiviksveien 40, N-5045 Bergen, Norway. voice: +47 55 95 93 55; fax +47 55 95 93 93 e-mail: [EMAIL PROTECTED] __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
[R] date to age
I have files which have columns of data that look like this:
DOB
9/27/1964
...
That is, dates in month/day/year format. When variables like DOB are read
in, they are converted to factors.
So, I wrote this to convert from date to age in years:
age-function(x)
{as.numeric(Sys.time()-strptime(as.character(x),format=%m/%d/%Y))/365.25}
This isn't very precise or pretty, but it works.
Does anybody have something better?
__
[EMAIL PROTECTED] mailing list
https://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] date to age
On Mon, 30 Jun 2003, William Briggs wrote:
I have files which have columns of data that look like this:
DOB
9/27/1964
...
That is, dates in month/day/year format. When variables like DOB are read
in, they are converted to factors.
Why? You can avoid that, of course.
So, I wrote this to convert from date to age in years:
age-function(x)
{as.numeric(Sys.time()-strptime(as.character(x),format=%m/%d/%Y))/365.25}
This isn't very precise or pretty, but it works.
Does anybody have something better?
Convert to POSIXlt and compare differences in years, months, days etc.
Write an extension to difftime() to handle years and contribute it?
--
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://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] Seemingly unrelated regressions
Is there an implementation of SUR in R? These are used commonly in economics. Thanks -- Richard A. Hinrichsen You can use the function 'sur' in the library 'systemfit'. Masaei Sato __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
[R] Deciphering an error message
Hello,
I'm working in spatstat and having difficulty with the ppp objects. I can get a ppp
object for one set of data, but with the same code applied to a second data set (all I
am changing is the field identifier), I get the following error message:
Error in switch(w$type, rectangle={: internal error: some total scores are neither 0
nor 1
Any thoughts on what this means and how to correct it would be most appreciated.
Thanks,
Suzanne
__
McAfee VirusScan Online from the Netscape Network.
Comprehensive protection for your entire computer. Get your free trial today!
http://channels.netscape.com/ns/computing/mcafee/index.jsp?promo=393397
Get AOL Instant Messenger 5.1 free of charge. Download Now!
__
[EMAIL PROTECTED] mailing list
https://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] Novice Questions
Hi, Bruce: I'm overwhelmed. Questioners seem to get quicker, more informative responses to questions that are short, well written and easily and quickly understood, and preferably include a toy example that someone else can run quickly to reproduce the problem and to evaluate alternative solutions. I see you are using source and would like to get more output. Did you check ?source? This function in R has arguments echo and verbose, which may produce what you want. If you've already tried that, then the problem may be output buffering, and I don't know how to modify that parameter. A search of www.r-project.org - search - R Site Search might help. Or ask a question focused specifically on that, giving also which version of R you are using under which operating system. I rarely use source. More often, I have R commands in another file and copy and paste into R the commands I want to run. That makes it easier for me to isolate errors, etc. This does not address all your questions, but it's a start. Hope this helps. spencer graves Bruce Moore wrote: I'm writing a program to perform linear regressions to estimate the number of bank teller transactions per hour of various types based upon day of week, time of day, week of month and several prices. I've got about 25,000 records in my dataset, 85 columns of transaction counts (used 1 at a time), about 50 columns of binary indicators (day, week, pay period, hour, branch), and a half dozen real valued prices. My program hangs on some regressions as I add interactions, probably due to logic problems in my code or collinearity problems in the data. 1) I'm running my program via the source() command. It appears that source() does not print any messages until it completes. Is there a way to get diagnostic messages to print immediately rather than when the source() command has completed? 2) I'm fairly certain that I've got some collinearity in the data set and the interactions. I've found an append (Ott Toomet 5/30/2003) that talks about a procedure to find collinearity problems using model.matrix() to generate the dataset with interactions and kappa() to determine the condition number of the matrix. Is there a more automated way to find collinear variables? 3) Is there a way to get lm() and/or step() or some other package to give a model with only coefficients that are significant at a particular level? 4) Is there a way to suppress display of a password when using the RODBC odbcConnect() function, or to get the function to prompt for a password? 5) What is the practical size limit on the number of terms in model? I know that I won't be able to consider all interactions, but would like to have some idea when to give up and go with what I've got. = Bruce Moore __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
[R] dev.copy()
In a batch script (i.e. there is no screen device), I would like to create both a PDF file and a PNG file from the same plot. I thought this would be the way to do it, but it isn't: R bitmap(copy.png, png16m, res=300) R pdf(copy.pdf) R plot(1:10, 1:10) # Plot into pdf file R dev.copy(which=2)# Copy to png file R dev.off(3) # Close pdf R dev.off(2) # Close png The PDF comes out fine, but the PNG appears blank. Any ideas what I'm doing wrong? TIA. -- -- David Brahm ([EMAIL PROTECTED]) __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
[R] Constructing loops in which i+1st element depends on ith
I feel greedy posting for help twice in one day- please forgive me, but the
thesis can't wait.
I have been trying to get an if
else statement working in a loop I am
writing, in which I specify a variable value to 9.2 (Wo) on the first
iteration, but for subsequent iterations, to adopt a value as a function of
variables from the previous iteration.
When I comment out the if
else statement, let W = Wo, and adjust the rest of
the file so I am reading the first row of the variables specified instead of
entire columns in my calculations, the calculations all work nicely without
errors - I get the numbers I ought to in one row of bio.
When I activate the loop and try to run the file with the if
.else, it looks
like it wants to work, but heres where it stalls;
Error in [-(*tmp*, i, value = ((bio[i - 1, 1] * bio[i - 1, 9])/Ef)) :
nothing to replace with
Execution halted
(see complete data file below)...
I guess its because it cant find the alternate case because it hasnt written
it yet.
So, my problem is two-fold:
1. How can I write my loop properly so that at the end of each iteration,
it records the row of data from bio such that I can cbind it back to my Day
data?
2. How can I specify the loop to use information from the i+1st element in
calculations for calculations in the ith?
Im pretty sure my problem is in where I create and specify files in the loop,
but beyond that, I dont know.
Heres the part of my command file thats giving me trouble. Everything before
this is simply specifying variable names to numbers, which is not giving be
problems.
#Bring in temp file
temper - scan(temp2.dat, na.strings = ., list(Day=0, Temp=0))
#Day = day on which iteration begins, starts at day 1, ends on 366
#Temp = temperature
Day - temper$Day ; Temp-temper$Temp ;
temp- cbind (Day, Temp)
#temp [,2]
p- 0.558626306252032
ACT - 1.66764519286918
Vc-((CTM-temp[,2])/(CTM-CTO))
Vr-((RTM-temp[,2])/(RTM-RTO))
comp- cbind (Day, Temp, Vc, Vr)
bio-NULL
M- length(Day) #number of days iterated
for (i in 1:M)
{
weight- function(Day)
{
W-NULL
if (Day[i]==1) W[i] - Wo
{W[i] - ((bio[i-1,1]*bio[i-1,9])/Ef)
}
W
}
W-weight(Day)
#W-Wo
C- p*CA*(W^CB)*((comp[,3]^Xc)*(exp(Xc*(1-comp[,3]*Pc
ASMR- (ACT*RA*(W^(RB))*((comp[,4]^Xa)*(exp(Xa*(1-comp[,4])
SMR- (ASMR/ACT)
A- (ASMR-SMR)
F- (FA*(comp[,2]^FB)*(exp(FG*p))*C)
U- (UA*(comp[,2]^UB)*(exp(UG*p))*(C-F))
SDA- (S*(C-F))
Gr- (C-(ASMR+F+U+SDA))
bio- rbind(c(W, C, ASMR, SMR, A, F, U, SDA, Gr))
dimnames (bio) -list(NULL, c
(W, C, ASMR, SMR, A, F, U, SDA, Gr))
}
bio
I would be grateful for any suggestions people might have.
Thanks,
Mike
--
Michael Rennie
M.Sc. Candidate
University of Toronto at Mississauga
3359 Mississauga Rd. N.
Mississauga ON L5L 1C6
Ph: 905-828-5452 Fax: 905-828-3792
__
[EMAIL PROTECTED] mailing list
https://www.stat.math.ethz.ch/mailman/listinfo/r-help
Re: [R] sample from a list of names for random groups
On 30 Jun 2003 at 17:11, Daniele Medri wrote: You should really try to specify better what you want. Lets try names # character vector with your names m - length(names) n1 - 5 n2 - 10 muestra - sample(names, m, replace=FALSE) muestra1 - muestra[1:n1] muestra2 - muestra[(n1+1):(n1+n2)] Is this what you want? Kjetil Halvorsen Dear R-users, I need to sample from a list of names (people) and create 2 random groups with unique item. Sure sample() function is a good point to start but I can't find example to solve my work. any tips? example? Thank -- Daniele Medri __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
[R] crossed random effects
Hi, I have a data set on germination and plant growth with the following variables: dataset=fm mass (response) sub (fixed effect) moist (fixed effect) pop (fixed effect) mum (random effect nested within population) iheight (covariate) plot (random effect- whole plot factor for split-plot design). I want to see if moist or sub interacts with mum for any of the pops, but I am getting an error message. This is the formula I used: fm$pmu - getGroups(fm, ~1|pop/mum, level=2) fm$grp = as.factor(rep(1,nrow(fm))) fm$pl - getGroups(fm, ~1|plot) fm$mo - getGroups(fm, ~1|moist) fm$su - getGroups(fm, ~1|sub) fm1 - lme(sqrt(mass) ~ iheight + moist*sub*pop, data=fm, random=list(grp=pdBlocked(list(pdIdent(~pl - 1), pdIdent(~pmu - 1), pdIdent(~pmu:su - 1), pdIdent(~pmu:mo - 1) Error in chol((value + t(value))/2) : non-positive definite matrix in chol I know the problem is with the random interaction terms, but I don't know how to overcome this. Any advice would be greatly appreciated. I'm new to R and analysis such as this. Thank you, Sarah Mclean [EMAIL PROTECTED] http://mobile.yahoo.com.au - Yahoo! Mobile - Check compose your email via SMS on your Telstra or Vodafone mobile. __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
[R] Creating a loop that works....
Hi there,
First off, thanks to everyone who has helped me so far. Sorry to keep
pestering you all.
I'm including my code here, and I will comment down it where it is that I am
having problems figuring out how to write this damn thing.
temper - scan(temp2.dat, na.strings = ., list(Day=0, Temp=0))
Read 366 records
Day - temper$Day ; Temp-temper$Temp ;
temp- cbind (Day, Temp)
#Day = number of days modelled, Temp = daily avg. temp.
#temp [,2]
p- 0.558626306252032
ACT - 1.66764519286918
Vc-((CTM-temp[,2])/(CTM-CTO))
Vr-((RTM-temp[,2])/(RTM-RTO))
comp- cbind (Day, Temp, Vc, Vr)
bio-NULL
M- length(Day) #number of days iterated
for (i in 1:M)
+ {
+
+ weight- function(Day)
+ {
+ W-NULL
+ if (Day[i]==1) {W[i] - Wo}
+ elseif (Day[i]1) {W[i] - ((bio[i-1,1]*bio[i-1,9])/Ef)
+ }
+ W
+ }
+
+ W-weight(Day)
The problem, as many of you have already identified, is right here. I hope I
finally have the syntax right, but even if the if else is coded properly, I
don't think R can find the values in the second condition I list. I need W in
each step of the iteration to change slightly, based on the mess of
calculations below (which are using parameters that I have already specified).
After all the calculations are made, I hope to get values in bio[i,1] and bio
[i,9] corresponding to the iteration that just occured, then return to the top
of the loop to combine them into the value of W for the next iteration. What I
think is happening here is that R is looking for values in the condition before
they are actually there- the way I've written it, they can't be there until I
get past the conditional step. Which means I am coding this all wrong. That
said, I'm not sure how else to do it; the value of W in the next iteration is
dependent on the values of Gr and W in the previous iteration, with the
exception of the first one (Day=1). I've tried defining bio as
bio-matrix(NA, ncol=9, nrow=366)
but that doesn't help either.
Perhaps my rbind at the end of the file is incorrect? I think maybe I'm getting
mixed up between calculating vectors and values-- should I be specifying [i]
for everything below where I am now specifying vecotrs?
+ #W-Wo
+
+ C- p*CA*(W^CB)*((comp[,3]^Xc)*(exp(Xc*(1-comp[,3]*Pc
+
+ ASMR- (ACT*RA*(W^(RB))*((comp[,4]^Xa)*(exp(Xa*(1-comp[,4])
+
+ SMR- (ASMR/ACT)
+
+ A- (ASMR-SMR)
+
+ F- (FA*(comp[,2]^FB)*(exp(FG*p))*C)
+
+ U- (UA*(comp[,2]^UB)*(exp(UG*p))*(C-F))
+
+ SDA- (S*(C-F))
+
+ Gr- (C-(ASMR+F+U+SDA))
+ #Day, Temp, Vc, Vr, W, C, ASMR, SMR, A, F, U, SDA, Gr)
+
+ bio- rbind(c(W, C, ASMR, SMR, A, F, U, SDA, Gr))
+
+ dimnames (bio) -list(NULL, c
(W, C, ASMR, SMR, A, F, U, SDA, Gr))
+
+ }
Error: length of dimnames[2] not equal to array extent
Execution halted
--
Michael Rennie
M.Sc. Candidate
University of Toronto at Mississauga
3359 Mississauga Rd. N.
Mississauga ON L5L 1C6
Ph: 905-828-5452 Fax: 905-828-3792
__
[EMAIL PROTECTED] mailing list
https://www.stat.math.ethz.ch/mailman/listinfo/r-help
RE: [R] Fitting inter-arrival time data
Unfortunately, the data are *non-negative*, not strictly positive. Zero is a valid and frequent inter-arrival time. It is, IIRC, the most likely value of a (negative) exponential distribution. -- M. Edward (Ed) Borasky mailto:[EMAIL PROTECTED] http://www.borasky-research.net Suppose that tonight, while you sleep, a miracle happens - you wake up tomorrow with what you have longed for! How will you discover that a miracle happened? How will your loved ones? What will be different? What will you notice? What do you need to explode into tomorrow with grace, power, love, passion and confidence? -- L. Michael Hall, PhD -Original Message- [snip] if you data are positive, you could use sm.density(..., positive=TRUE) __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
RE: [R] Fitting inter-arrival time data
Thanks!! It does look like the easiest thing is direct ML; the code for a normal mixture is in the book, so all I have to do is modify that for a sum of a hyper-exponential, for which I have an approximate mean and CV, and a normal, for which I have an approximate mean and SD. I have two big peaks, one near zero which is probably hyperexponential with a CV about 3, and the other near 600 seconds (a refresh that happens every ten minutes) which looks Gaussian with a very small standard deviation. I think what I'm going to do is fit the two peaks using ML, since I know where they are, then subtract them out and look at the structure of the residuals. The stuff over 600 seconds is sparse and totally uninteresting. After I'm done with this, I get to look at the distribution of the network traffic. The good news is that I get those inter-arrival times to the nearest microsecond. :) -- M. Edward (Ed) Borasky mailto:[EMAIL PROTECTED] http://www.borasky-research.net Suppose that tonight, while you sleep, a miracle happens - you wake up tomorrow with what you have longed for! How will you discover that a miracle happened? How will your loved ones? What will be different? What will you notice? What do you need to explode into tomorrow with grace, power, love, passion and confidence? -- L. Michael Hall, PhD -Original Message- [snip] For all of these see MASS (the book) and its on-line complements. __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
[R] crossed random effects
Hi, if I have posted this twice, please ignore this. I'm not sure if I sent it to the correct e-mail address the first time. I have a data set on germination and plant growth with the following variables: dataset=fm mass (response) sub (fixed effect) moist (fixed effect) pop (fixed effect) mum (random effect nested within population) iheight (covariate) plot (random effect- whole plot factor for split-plot design). I want to see if moist or sub interacts with mum for any of the pops, but I am getting an error message. This is the formula I used: fm$pmu - getGroups(fm, ~1|pop/mum, level=2) fm$grp = as.factor(rep(1,nrow(fm))) fm$pl - getGroups(fm, ~1|plot) fm$mo - getGroups(fm, ~1|moist) fm$su - getGroups(fm, ~1|sub) fm1 - lme(sqrt(mass) ~ iheight + moist*sub*pop, data=fm, random=list(grp=pdBlocked(list(pdIdent(~pl - 1), pdIdent(~pmu - 1), pdIdent(~pmu:su - 1), pdIdent(~pmu:mo - 1) Error in chol((value + t(value))/2) : non-positive definite matrix in chol I know the problem is with the random interaction terms, but I don't know how to overcome this. Any advice would be greatly appreciated. I'm new to R and analysis such as this. Thank you, Sarah Mclean [EMAIL PROTECTED] http://mobile.yahoo.com.au - Yahoo! Mobile - Check compose your email via SMS on your Telstra or Vodafone mobile. __ [EMAIL PROTECTED] mailing list https://www.stat.math.ethz.ch/mailman/listinfo/r-help
