[R] Impute Values for Forest Inventory
Dear All, I am Ricky Jacob, a project Student from India who is working on Forest Inventories. Input data: Plot(area = .1 ha) data having the following information: 1) Basal Area 2)Tree Density 3)Volume So I am applying this information to the corresponding pixels in the satellite imagery of the study area. I also have given the same values to a 3x3 window around that pixel. Inventory is taken compartmentwise and so this information of all the plots in a compartment is taken and generalised over all the pixels falling in that compartment. To make the estimation more realistic, i decided to use the impute opton in r. The yai requires me to enter the x and y variable. I stll haven't figured out how i should put my datasets to impute the values of variables like Basal area, volume for only those pixels for which no data is available. is msn or randomforest a better option. I tried to work on the example MoscowMtStJoe dataset. But I wasn't able to figure out how I should put in my data. I have records which have both satellite and attribute data and also have records with only satellite data. I need to impute attribute data into those records alone for which no attribute data is available without altering values in the records having the attribute information. Hope for a response Regards Ricky Jacob __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] C interface
Hi All
I have read this document - An Introduction to the .C Interface to R,
which primarily tells how to interface C language with R.
Is there and more elaborative and online documentation regarding this
interface.
Any pointers appreciated
-thanks
-gaurav
DISCLAIMER AND CONFIDENTIALITY CAUTION:\ \ This message and ...{{dropped}}
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
[R] Tail area of sum of Chi-square variables
Dear R experts, I was wondering if there are any R functions that give the tail area of a sum of chisquare distributions of the type: a_1 X_1 + a_2 X_2 where a_1 and a_2 are constants and X_1 and X_2 are independent chi-square variables with different degrees of freedom. Thanks, Klaus -- Feel free - 5 GB Mailbox, 50 FreeSMS/Monat ... __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Plot degree symbol by itself
Dear all, I'm trying to plot the degree symbol by itself between two square brackets. I just want to have K [°]. So far I got to: expression(K ~ group([,1*degree,])) or expression(K ~ group([,1^o,])) But it won't work without a number or letter. Any suggestions? Thanks, andre __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Tail area of sum of Chi-square variables
Hi Klausch: I was wondering if there are any R functions that give the tail area of a sum of chisquare distributions of the type: a_1 X_1 + a_2 X_2 where a_1 and a_2 are constants and X_1 and X_2 are independent chi-square variables with different degrees of freedom. Christian Kleiber (Cc on this reply) has code for computing the distribution function of general linear combinations of chi-squared variables. It's not yet on CRAN, but just ask him for a devel-snapshot. Best wishes, Z __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] C interface
We don't know what document that is, and you haven't given us a useful
pointer, have you? And the authors (presumably Roger Peng and Jan de
Leeuw) deserve credit.
The definitive documentation is the 'Writing R Extensions' manual which
ships with R. There is also a lot in 'S Programming' (see the books in
the FAQ), and many examples in the R sources and contributed packages.
On Thu, 29 Mar 2007, [EMAIL PROTECTED] wrote:
Hi All
I have read this document - An Introduction to the .C Interface to R,
which primarily tells how to interface C language with R.
Is there and more elaborative and online documentation regarding this
interface.
Any pointers appreciated
-thanks
-gaurav
DISCLAIMER AND CONFIDENTIALITY CAUTION:\ \ This message and ...{{dropped}}
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
--
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
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Re: [R] Plot degree symbol by itself
Andre Jung wrote: Dear all, I'm trying to plot the degree symbol by itself between two square brackets. I just want to have K [°]. So far I got to: expression(K ~ group([,1*degree,])) or expression(K ~ group([,1^o,])) But it won't work without a number or letter. This worked for me: expression(K ~ group([,degree,])) Any suggestions? Thanks, andre __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- Henrik Andersson Danish Meteorological Institute Lyngbyvej 100 2100 Copenhagen Ø Denmark Tel: +45 39157215 Email: [EMAIL PROTECTED] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Plot degree symbol by itself
Andre Jung wrote:
Dear all,
I'm trying to plot the degree symbol by itself between two square
brackets. I just want to have K [°]. So far I got to:
expression(K ~ group([,1*degree,]))
or
expression(K ~ group([,1^o,]))
But it won't work without a number or letter.
Any suggestions?
An empty pair of braces usually works:
plot(0)
text(1,1,expression(K ~ group([,{}*degree,])))
(or {}^degree, but that looks odd -- degree is already a raised symbol)
But whatever was wrong with just
text(1.2,1,expression(K ~ group([,degree,])))
??
Thanks,
andre
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Re: [R] Large matrix into a vector
Hi All, Thank you very much for all your suggestions. It's a great learning for me. All the three suggested solutions seem working. I don't know what 'side effects' that you were talking about. To summarize the responses: s - read.table(sample.txt, sep=\t) s1 - as.matrix(s) s1 V1 V2 V3 1 0.59 0.47 0.44 2 0.85 0.42 0.57 3 0.48 0.57 0.57 4 0.61 0.24 0.24 5 0.38 0.21 0.36 6 0.65 0.42 1.50 7 0.49 0.23 0.42 8 0.60 0.51 0.53 9 0.00 0.00 0.00 s2 - as.vector(s1) s2 [1] 0.59 0.85 0.48 0.61 0.38 0.65 0.49 0.60 0.00 0.47 0.42 0.57 0.24 0.21 0.42 0.23 0.51 0.00 0.44 0.57 0.57 0.24 0.36 [24] 1.50 0.42 0.53 0.00 s3 - c(s1) s3 [1] 0.59 0.85 0.48 0.61 0.38 0.65 0.49 0.60 0.00 0.47 0.42 0.57 0.24 0.21 0.42 0.23 0.51 0.00 0.44 0.57 0.57 0.24 0.36 [24] 1.50 0.42 0.53 0.00 s3 - s1 dim(s3) - NULL s3 [1] 0.59 0.85 0.48 0.61 0.38 0.65 0.49 0.60 0.00 0.47 0.42 0.57 0.24 0.21 0.42 0.23 0.51 0.00 0.44 0.57 0.57 0.24 0.36 [24] 1.50 0.42 0.53 0.00 Interestingly, if I apply the same three solutions to the data.frame 's', the results are different: (1) as.vector() keeps the data frame as it is. (2) c() changes into lists, and (3) making dim() - NULL keeps as structure. Thanks again. Kind regards, Ezhil --- Peter Dalgaard [EMAIL PROTECTED] wrote: Marc Schwartz [EMAIL PROTECTED] writes: On Wed, 2007-03-28 at 19:55 -0200, Alberto Monteiro wrote: Prof Brian Ripley wrote: We have already seen three solutions. I don't like to see the use of c() for its side effects. In this case Marc's as.vector seems to me to be self-explanatory, and that is a virtue in programming that is too often undervalued. I agree; but for our enlightnment, what are the side effects of c()? Alberto Monteiro I believe that Prof. Ripley is referring to the following, from the Details section in ?c: c is sometimes used for its side effect of removing attributes except names, for example to turn an array into a vector. as.vector is a more intuitive way to do this, but also drops names. There are also examples in ?c of this behavior. The terminology is a bit unfortunate, though. Side effect usually means an effect that is not reflected in the return value of a function, like printing, plotting, or assignment. -- O__ Peter Dalgaard Øster Farimagsgade 5, Entr.B c/ /'_ --- Dept. of Biostatistics PO Box 2099, 1014 Cph. K (*) \(*) -- University of Copenhagen Denmark Ph: (+45) 35327918 ~~ - ([EMAIL PROTECTED]) FAX: (+45) 35327907 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. Food fight? Enjoy some healthy debate __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] gls bug?
On Fri, 16 Mar 2007, simon bond wrote: I found that the following code crashes R (version 2.4.0 in windows). x=rnorm(10,0.1,1) library(nlme) gls(x~0) I quickly found a work-around for what I was trying to do, but I thought I should report this. This will be fixed (to give a sensible non-fatal error message) in nlme 3.1-80. If you are still using 2.4.0 you probably have not updated your recommended packages either: please use sessionInfo() in bug reports as requested in the R posting guide. -- 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 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] C interface
On 3/29/07, Prof Brian Ripley [EMAIL PROTECTED] wrote:
We don't know what document that is, and you haven't given us a useful
pointer, have you? And the authors (presumably Roger Peng and Jan de
Leeuw) deserve credit.
It is a great point. I have googled and confirm that the authors are
Roger Peng and Jan de
Leeuw. Here is the link
http://www.biostat.jhsph.edu/~rpeng/docs/interface.pdf
The definitive documentation is the 'Writing R Extensions' manual which
ships with R. There is also a lot in 'S Programming' (see the books in
the FAQ), and many examples in the R sources and contributed packages.
On Thu, 29 Mar 2007, [EMAIL PROTECTED] wrote:
Hi All
I have read this document - An Introduction to the .C Interface to R,
which primarily tells how to interface C language with R.
Is there and more elaborative and online documentation regarding this
interface.
Any pointers appreciated
-thanks
-gaurav
DISCLAIMER AND CONFIDENTIALITY CAUTION:\ \ This message and ...{{dropped}}
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
--
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
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
--
Ronggui Huang
Department of Sociology
Fudan University, Shanghai, China
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
[R] Fanny Clustering
Dear R-Helpers, I'd like to develop a fanny clustering on my data set(70.000 rows), but when i run the procedure i obtain this error: error in vector(double, lenght): too big dimension for the selected vector. How can i solve this problem? Thank you in advance. Sergio Della Franca. [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Fanny Clustering
1) Reduce the size of your sample (random or stratified subsampling), 2) Increase the memory of your computer available to R. Best, Philippe Grosjean ..°})) ) ) ) ) ) ( ( ( ( (Prof. Philippe Grosjean ) ) ) ) ) ( ( ( ( (Numerical Ecology of Aquatic Systems ) ) ) ) ) Mons-Hainaut University, Belgium ( ( ( ( ( .. Sergio Della Franca wrote: Dear R-Helpers, I'd like to develop a fanny clustering on my data set(70.000 rows), but when i run the procedure i obtain this error: error in vector(double, lenght): too big dimension for the selected vector. How can i solve this problem? Thank you in advance. Sergio Della Franca. [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] creating conditional list of elements
Sorry to plague the list, but I think I got the answer. The following
would do:
signalList - list(tradingRules$Signal[tradingRules$Enabled]) [[1]]
length(signalList)
[1] 2
Now my problem is shifted: I have the Signal column in the original data
frame referring to actual
matrices previously created in R. That is, bar_signal and cif_signal are
extant matrices. What I
need is the minimum number of rows in these matrices, so what I plan to do
is:
n - min(sapply(signalList, NROW))
but this doesn't work (it returns 1, but I have 2800 rows in each of
bar_signal and cif_signal, so I should
get 2800)
Is there a smart way to do this? And is there a way to tell R that the
entries in the Signal column
of tradingSignal are the names of objects?
Thanks,
Murali
Murali Menon/GB/ABNAMRO/NL
29/03/2007 11:13
To
r-help@stat.math.ethz.ch
cc
Subject
creating conditional list of elements
Folks,
I have a matrix as follows (first column is the rownames, first row is the
columnnames)
RuleEnabled Signal
Foo False foo_signal
Bar Truebar_signal
Gum False gum_signal
Cif Truecif_signal
I would like to create a list of only those signals whose 'enabled' flag
is True. So in the above
case I should end up with
signalList = bar_signal, cif_signal
Likewise, if the enabled flags were all set to False, then signalList
should be an empty list.
What's a good way to achieve this, please?
Thanks,
Murali
---
This message (including any attachments) is confidential and...{{dropped}}
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Re: [R] Fanny Clustering
Ok, How can i increase the memory of your computer available to R? 2007/3/29, Philippe Grosjean [EMAIL PROTECTED]: 1) Reduce the size of your sample (random or stratified subsampling), 2) Increase the memory of your computer available to R. Best, Philippe Grosjean ..°})) ) ) ) ) ) ( ( ( ( (Prof. Philippe Grosjean ) ) ) ) ) ( ( ( ( (Numerical Ecology of Aquatic Systems ) ) ) ) ) Mons-Hainaut University, Belgium ( ( ( ( ( .. Sergio Della Franca wrote: Dear R-Helpers, I'd like to develop a fanny clustering on my data set(70.000 rows), but when i run the procedure i obtain this error: error in vector(double, lenght): too big dimension for the selected vector. How can i solve this problem? Thank you in advance. Sergio Della Franca. [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Fanny Clustering
Sergio Della Franca wrote: Ok, How can i increase the memory of your computer available to R? Well, if you would like to increase memory of MY computer... you are welcome to do so... but I doubt it would be of any use for you ;-) You don't tell us how much RAM you have currently, which platform you use, etc... The general approach is to use a computer with more RAM, up to the limit permitted by a 32-bit system for R, and then, to switch to a 64-bit version under Linux, if you need even more RAM. The other proposed solution is not stupid. With 70.000 cases, you have a fairly large dataset. You don't tell use how many groups you expect from your clustering, but it is often better to use a couple of tens, or hundreds of representative cases for each group, no more. In supervised classification, it is easier to build such a training set with relatively balanced number of items in each group, because targeted classification is known a priori from the manual classification provided. With unsupervised classification, you could either try a pure random subsampling, or select your subsample based on similarity according to a given distance measurement. I did something like that using a Malahanobis distance, MDS, and then, stratified subsampling inside a regular grid placed on top of the MDS plot. Otherwise, I am not a specialist of unsupervised classification, and other people here could have better suggestion. Best, Philippe Grosjean 2007/3/29, Philippe Grosjean [EMAIL PROTECTED]: 1) Reduce the size of your sample (random or stratified subsampling), 2) Increase the memory of your computer available to R. Best, Philippe Grosjean ..°})) ) ) ) ) ) ( ( ( ( (Prof. Philippe Grosjean ) ) ) ) ) ( ( ( ( (Numerical Ecology of Aquatic Systems ) ) ) ) ) Mons-Hainaut University, Belgium ( ( ( ( ( .. Sergio Della Franca wrote: Dear R-Helpers, I'd like to develop a fanny clustering on my data set(70.000 rows), but when i run the procedure i obtain this error: error in vector(double, lenght): too big dimension for the selected vector. How can i solve this problem? Thank you in advance. Sergio Della Franca. [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] composed matrices
I have just started programming in R and so my question might be basic but I cant find it in the manual I have four matrices A,B,C and D and want them to compose in a big matrix X with A in the upper left corner, B in the right upper corner, c below A and D below B. Thanks for your help eva __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] composed matrices
try this: A1 - matrix(1:20, 5, 4) B1 - matrix(1:15, 5, 3) A2 - matrix(1:8, 2, 4) B2 - matrix(1:6, 2, 3) # rbind(cbind(A1, B1), cbind(A2, B2)) 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/(0)16/336899 Fax: +32/(0)16/337015 Web: http://med.kuleuven.be/biostat/ http://www.student.kuleuven.be/~m0390867/dimitris.htm - Original Message - From: Eva Ubl [EMAIL PROTECTED] To: r-help@stat.math.ethz.ch Sent: Thursday, March 29, 2007 1:10 PM Subject: [R] composed matrices I have just started programming in R and so my question might be basic but I cant find it in the manual I have four matrices A,B,C and D and want them to compose in a big matrix X with A in the upper left corner, B in the right upper corner, c below A and D below B. Thanks for your help eva __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. Disclaimer: http://www.kuleuven.be/cwis/email_disclaimer.htm __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] composed matrices
Eva Ubl wrote: I have just started programming in R and so my question might be basic but I cant find it in the manual I have four matrices A,B,C and D and want them to compose in a big matrix X with A in the upper left corner, B in the right upper corner, c below A and D below B. A - matrix(1:4, ncol=2) B - matrix(5:8, ncol=2) C - matrix(9:12, ncol=2) D - matrix(13:16, ncol=2) rbind(cbind(A,B), cbind(C,D)) [,1] [,2] [,3] [,4] [1,]1357 [2,]2468 [3,]9 11 13 15 [4,] 10 12 14 16 ?rbind ?cbind Thanks for your help eva __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- Chuck Cleland, Ph.D. NDRI, Inc. 71 West 23rd Street, 8th floor New York, NY 10010 tel: (212) 845-4495 (Tu, Th) tel: (732) 512-0171 (M, W, F) fax: (917) 438-0894 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] equivalent datatypes
Hallo, can anyone help me with datatypes? Which datatypes from R are equivalent to the following ones from C? C datatypes: - double array - struct array - cell array - char array - logical array Thanks, Corinna __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Tail area of sum of Chi-square variables
I was wondering if there are any R functions that give the tail area
of a sum of chisquare distributions of the type:
a_1 X_1 + a_2 X_2
where a_1 and a_2 are constants and X_1 and X_2 are independent
chi-square variables with different degrees of freedom.
You might also check out Welch and Satterthwaite's (separate) papers on
effective degrees of freedom for compound estimates of variance, which led to a
thing called the welch-satterthwaite equation by one (more or less notorious,
but widely used) document called the ISO Guide to Expression of Uncertainty in
Measurement (ISO, 1995). The original papers are
B. L. Welch, J. Royal Stat. Soc. Suppl.(1936) 3 29-48
B. L. Welch, Biometrika, (1938) 29 350-362
B. L. Welch, Biometrika, (1947) 34 28-35
F. E. Satterthwaite, Psychometrika (1941) 6 309-316
F. E. Satterthwaite, Biometrics Bulletin, (1946) 2 part 6 110-114
The W-S equation - which I believe is a special case of Welch's somewhat more
general treatment - says that if you have multiple independent estimated
variances v[i] (could be more or less equivalent to your a_i X_i?) with degrees
of freedom nu[i], the distribution of their sum is approximately a scaled
chi-squared distribution with effective degrees of freedom nu.effective given by
nu.effective = sum(v[i])^2 / sum((v[i]^2)/nu[i] )
If I recall correctly, with an observed variance s^2 (corresponding to the
sum(v[i] above if those are observed varianes), nu*(s^2 /sigma^2) is
distributed as chi-squared with degrees of freedom nu, so the scaling factor
for quantiles would come out of there (depending whether you're after the tail
areas for s^2 given sigma^2 or for a confidence interval for sigma^2 given s^2)
However, I will be most interested to see what a more exact calculation
provides!
Steve Ellison
***
This email and any attachments are confidential. Any use, co...{{dropped}}
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Re: [R] equivalent datatypes
On 3/29/2007 6:45 AM, Schmitt, Corinna wrote: Hallo, can anyone help me with datatypes? Which datatypes from R are equivalent to the following ones from C? I assume you mean functionally equivalent; if you mean equivalent in storage so you can pass them to C functions, see the Writing R Extensions manual. C datatypes: - double array A numeric vector. - struct array R has no exact equivalent. A struct is similar to a list, but there is no enforcement of types in a list. You could also implement a struct as an S4 object to get some type safety. An array of structs would usually be done in R as a list of arrays, but could be done as a list of lists. - cell array I don't know what a cell is in C. - char array A single element character vector. - logical array A logical vector. Duncan Murdoch __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] what is the difference between survival analysis and (...)
Thomas Lumley wrote: On Wed, 28 Mar 2007, Frank E Harrell Jr wrote: Eric Elguero wrote: Hi everybody, recently I had to teach a course on Cox model, of which I am not a specialist, to an audience of medical epidemiologists. Not a good idea you might say.. anyway, someone in the audience was very hostile. At some point, he sayed that Cox model was useless, since all you have to do is count who dies and who survives, divide by the sample sizes and compute a relative risk, and if there was significant censoring, use cumulated follow-up instead of sample sizes and that's it! I began arguing that in Cox model you could introduce several variables, interactions, etc, then I remembered of logistic models ;-) The only (and poor) argument I could think of was that if mr Cox took pains to devise his model, there should be some reason... That is a very ignorant person, concerning statistical efficiency/power/precision and how to handle incomplete follow-up (variable follow-up duration). There are papers in the literature (I wish I had them at my fingertips) that go into the efficiency loss of just counting events. If the events are very rare, knowing the time doesn't help as much, but the Cox model still can handle censoring correctly and that person's approach doesn't. Certainly just counting the events is inefficient -- the simplest example would be studies of some advanced cancers where nearly everyone dies during followup, so that there is little or no censoring but simple counts are completely uninformative. It's relatively hard to come up with an example where using the total-time-on-test (rather than sample size) as a denominator is much worse than the Cox mode, though. You need the baseline hazard to vary a lot over time and the censoring patterns to be quite different in the groups, but proportional hazards to still hold. I think the advantages of the Cox model over a reasonably sensible person-time analysis are real, but not dramatic -- it would be hard to find a data set that would convince the sort of person who would make that sort of claim. I would argue that computational convenience on the one hand, and the ability to exercise lots of nice mathematical tools on the other hand have also contributed to the continuing popularity of the Cox model. -thomas Thomas LumleyAssoc. Professor, Biostatistics [EMAIL PROTECTED]University of Washington, Seattle Nicely put Thomas. I have seen examples from surgical research where the hazard function is bathtub shaped and the epidemiologist's use of the exponential distribution is very problematic. I have also seen examples in acute illness and medical treatment where time until death is important even with only 30-day follow-up. Frank -- Frank E Harrell Jr Professor and Chair School of Medicine Department of Biostatistics Vanderbilt University __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] creating conditional list of elements
John,
Thanks, that works nicely. Didn't know about 'get'.
Onwards and upwards! :-)
Cheers,
Murali
John James [EMAIL PROTECTED]
29/03/2007 12:40
To
[EMAIL PROTECTED]
cc
Subject
RE: [R] creating conditional list of elements
Murali
If sm is your orginal matrix
# such that
sm[sm$Enabled,]$Signal
[1] bar_signal cif_signal
# and
bar_signal - matrix(rnorm(100), nrow=5, ncol=20)
cif_signal - matrix(rnorm(60), nrow=12, ncol=5)
# then...
sapply(sm[sm$Enabled,]$Signal, function(x){NROW(get(x))})
bar_signal cif_signal
5 12
Hope this helps
John James
Mango Solutions
-Original Message-
From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED]
Sent: 29 March 2007 11:40
Cc: r-help@stat.math.ethz.ch
Subject: Re: [R] creating conditional list of elements
Sorry to plague the list, but I think I got the answer. The following
would do:
signalList - list(tradingRules$Signal[tradingRules$Enabled]) [[1]]
length(signalList)
[1] 2
Now my problem is shifted: I have the Signal column in the original data
frame referring to actual
matrices previously created in R. That is, bar_signal and cif_signal are
extant matrices. What I
need is the minimum number of rows in these matrices, so what I plan to do
is:
n - min(sapply(signalList, NROW))
but this doesn't work (it returns 1, but I have 2800 rows in each of
bar_signal and cif_signal, so I should
get 2800)
Is there a smart way to do this? And is there a way to tell R that the
entries in the Signal column
of tradingSignal are the names of objects?
Thanks,
Murali
Murali Menon/GB/ABNAMRO/NL
29/03/2007 11:13
To
r-help@stat.math.ethz.ch
cc
Subject
creating conditional list of elements
Folks,
I have a matrix as follows (first column is the rownames, first row is the
columnnames)
RuleEnabled Signal
Foo False foo_signal
Bar Truebar_signal
Gum False gum_signal
Cif Truecif_signal
I would like to create a list of only those signals whose 'enabled' flag
is True. So in the above
case I should end up with
signalList = bar_signal, cif_signal
Likewise, if the enabled flags were all set to False, then signalList
should be an empty list.
What's a good way to achieve this, please?
Thanks,
Murali
---
This message (including any attachments) is confidential and...{{dropped}}
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide
http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
---
This message (including any attachments) is confidential and...{{dropped}}
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
[R] Kmeans centers
Dear R-Helpers, I read in the R documentation, about kmeans: centers Either the number of clusters or a set of initial (distinct) cluster centres. *If a number*, a random set of (distinct) rows in x is chosen as the initial centres. My question is: could it be possible that the centers are character and not number? Thank you in advance. Sergio Della Franca [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Large matrix into a vector
On Thu, 2007-03-29 at 02:12 -0700, A Ezhil wrote: Hi All, Thank you very much for all your suggestions. It's a great learning for me. All the three suggested solutions seem working. I don't know what 'side effects' that you were talking about. As Peter noted, the phrase 'side effect' may be sub-optimal. However, I would use the interpretation that in this case, the removal of dim attributes on a single object as a consequence of the use of c(), though documented, is not the primary intended purpose of the function. Stated differently, perhaps in a manner consistent with Prof. Ripley's reply, the coercion of a matrix to a vector by the use of c(), is applying a function to an object to gain the benefit of behavior that is secondary to the intended functionality of combining objects. To summarize the responses: s - read.table(sample.txt, sep=\t) s1 - as.matrix(s) s1 V1 V2 V3 1 0.59 0.47 0.44 2 0.85 0.42 0.57 3 0.48 0.57 0.57 4 0.61 0.24 0.24 5 0.38 0.21 0.36 6 0.65 0.42 1.50 7 0.49 0.23 0.42 8 0.60 0.51 0.53 9 0.00 0.00 0.00 s2 - as.vector(s1) s2 [1] 0.59 0.85 0.48 0.61 0.38 0.65 0.49 0.60 0.00 0.47 0.42 0.57 0.24 0.21 0.42 0.23 0.51 0.00 0.44 0.57 0.57 0.24 0.36 [24] 1.50 0.42 0.53 0.00 s3 - c(s1) s3 [1] 0.59 0.85 0.48 0.61 0.38 0.65 0.49 0.60 0.00 0.47 0.42 0.57 0.24 0.21 0.42 0.23 0.51 0.00 0.44 0.57 0.57 0.24 0.36 [24] 1.50 0.42 0.53 0.00 s3 - s1 dim(s3) - NULL s3 [1] 0.59 0.85 0.48 0.61 0.38 0.65 0.49 0.60 0.00 0.47 0.42 0.57 0.24 0.21 0.42 0.23 0.51 0.00 0.44 0.57 0.57 0.24 0.36 [24] 1.50 0.42 0.53 0.00 Interestingly, if I apply the same three solutions to the data.frame 's', the results are different: (1) as.vector() keeps the data frame as it is. (2) c() changes into lists, and (3) making dim() - NULL keeps as structure. That's because the underlying structure of a data frame is a list, whereas a matrix is a vector. HTH, Marc snip __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] using alpha transparency for lines in levelplot - SUMMARY
I reported a similar issue with Adobe Reader in a thread starting here: http://tolstoy.newcastle.edu.au/R/e2/devel/06/10/0706.html K Wright On 3/27/07, Michael Sumner [EMAIL PROTECTED] wrote: Hello, thanks to Deepayan Sarkar for sorting me out on this one. The problem with transparent lines affecting region colour in lattice plot appears when using Adobe Reader (v 8 in my case). I've only viewed the file on Windows XP. I've tried using Foxit Reader to view the file and there's no problem. Cheers, Mike. __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Tail area of sum of Chi-square variables
On Thu, 29 Mar 2007, Klaus Nordhausen wrote: I was wondering if there are any R functions that give the tail area of a sum of chisquare distributions of the type: a_1 X_1 + a_2 X_2 where a_1 and a_2 are constants and X_1 and X_2 are independent chi-square variables with different degrees of freedom. pchisqsum() in the survey package does this. -thomas Thomas Lumley Assoc. Professor, Biostatistics [EMAIL PROTECTED] University of Washington, Seattle __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] two questions about ccf
Hi, I have two questions about ccf. 1) does it return correlation value for each lag? The documentation states the following: The lag is returned and plotted in units of time, and not numbers of observations. There are printand subsetting methods for objects of class acf . Does this mean only lag values are returned, and if plot is turned off, then we won't know the calculated correlation value for each lag? Is there a way to display both the lag and its corresponding correlation value in text? 2) Is the lag used for ccf always in units of time? The documentation states: The lag is returned and plotted in units of time, and not numbers of observations.. This makes sense for acf, but does ccf lag also use units of time instead of observations? Thanks, Tom [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Kmeans centers
On Thu, 2007-03-29 at 15:02 +0200, Sergio Della Franca wrote: Dear R-Helpers, I read in the R documentation, about kmeans: centers Either the number of clusters or a set of initial (distinct) cluster centres. *If a number*, a random set of (distinct) rows in x is chosen as the initial centres. My question is: could it be possible that the centers are character and not number? I think you misunderstand - centers is the number of clusters you want to partition your data into. How else would you specify the number of clusters other than by a number? So no, it has to be a numeric number. The alternative use of centers is to provide known starting points for the algorithm, such as from the results of a hierarchical cluster analysis, that are the locations of the cluster centroids, for each cluster, on each of the feature variables. Also, argument x to kmeans() is specific about requiring a numeric matrix (or something coercible to one), so characters here are not allowed either. But then again, I may not have understood what it is that you are asking, but that is not surprising given that you have not provided an example of what you are trying to do, and how you tried to do it but failed. and provide commented, minimal, self-contained, reproducible code. ^^^ G -- %~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~% Gavin Simpson [t] +44 (0)20 7679 0522 ECRC, UCL Geography, [f] +44 (0)20 7679 0565 Pearson Building, [e] gavin.simpsonATNOSPAMucl.ac.uk Gower Street, London [w] http://www.ucl.ac.uk/~ucfagls/ UK. WC1E 6BT. [w] http://www.freshwaters.org.uk %~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~% __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Bonferroni p-value greater than 1
Thank you John and Peter. Peter, yes I'm guilty of tacking onto a random mail. I thought you couldn't tell since I got ride of the text from the last mail. Apologize. H. John Fox [EMAIL PROTECTED] 3/28/2007 5:37 PM Dear Horace, The Bonferonni p-value is obtained from the unadjusted p-value by multiplying the latter by the number of observations, and provides a conservative (although usually quite accurate) outlier test. When the adjusted p-value exceeds 1 you can take that as an indication that there are no unusually large studentized residuals (and indeed that the largest studentized residual is smaller than one would expect under the standard linear-model assumptions). I hope this helps, John John Fox Department of Sociology McMaster University Hamilton, Ontario Canada L8S 4M4 905-525-9140x23604 http://socserv.mcmaster.ca/jfox -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Horace Tso Sent: Wednesday, March 28, 2007 6:36 PM To: 'R R-help' Subject: [R] Bonferroni p-value greater than 1 Hi folks, I use the outlier.test in package car to test a lm model and the bonferroni p value returned is shown as NA. When the object is typed it indicates the p value is greater than 1. I'm not sure how to interpret it. Thanks in advance. Horace W. Tso outlier.test(mod)$test max|rstudent|df unadjusted p Bonferroni p 2.04106376 18.0.05618628NA outlier.test(mod) max|rstudent| = 2.041064, degrees of freedom = 18, unadjusted p = 0.05618628, Bonferroni p 1 Observation: 1 The lm model looks fine to me, summary(mod) Call: lm(formula = x ~ ind, na.action = na.fail) Residuals: Min 1Q Median 3Q Max -1.2082 -0.5200 0.1309 0.5725 0.9593 Coefficients: Estimate Std. Error t value Pr(|t|) (Intercept) 59.845860.31900 187.6 2e-16 *** ind -0.167680.02541-6.6 2.57e-06 *** --- Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1 Residual standard error: 0.705 on 19 degrees of freedom Multiple R-Squared: 0.6963, Adjusted R-squared: 0.6803 F-statistic: 43.56 on 1 and 19 DF, p-value: 2.57 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] tcltk, tclRequire and Tktable help
I know almost nothing about the tcltk library, and the documentation seems very poor. What's the meaning of this error, and is there any way to fix it? I'm running R 2.4.1 in a Windows XP machine where I have almost no privileges (but at home I am the Evil Overlord of a Linux machine...) library(tcltk) tclRequire(Tktable) # [1] FALSE # Warning message: # Tcl package 'Tktable' not found in: tclRequire(Tktable) Alberto Monteiro __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] E-Mail/Post Threading (was: Bonferroni p-value greater than 1)
On Thu, 2007-03-29 at 09:51 -0700, Horace Tso wrote: Thank you John and Peter. Peter, yes I'm guilty of tacking onto a random mail. I thought you couldn't tell since I got ride of the text from the last mail. Apologize. H. Just a quick heads up here, that deleting the body text of a message or changing the subject line, does not alter the 'linkage' between posts. There are standards for how messages are 'threaded' and largely have to do with the e-mail headers, not the e-mail content. A couple of quick references that might be helpful: http://people.dsv.su.se/~jpalme/ietf/message-threading.html http://www.jwz.org/doc/threading.html HTH, Marc Schwartz __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] pipe Apple
Hi, I have a student trying to run R on an Apple (OS 10.3.9). She tried to cut-and-paste the data via the code: data-read.table(pipe(pbpaste)) But she keeps getting the error message: 'error in pipe(pbpaste): pipe connections are not available on this system' I do not know much about using an Apple. Has anyone run into this before? Does anyone have any ideas for how to fix the problem? Thanks! Alex -- *** A. Alexander Beaujean, Ph.D., LSSP Licensed Psychologist (Provisional, TX) http://myprofile.cos.com/abeaujean http://www.baylor.edu/soe/faculty/index.php?id=38476 General impressions are never to be trusted. Unfortunately when they are of long standing they become fixed rules of life, and assume a prescriptive right not to be questioned. Consequently those who are not accustomed to original inquiry entertain a hatred and a horror of statistics. They cannot endure the idea of submitting their sacred impressions to cold-blooded verification. But it is the triumph of scientific men to rise superior to such superstitions, to devise tests by which the value of beliefs may be ascertained, and to feel sufficiently masters of themselves to discard contemptuously whatever may be found untrue. --Sir Francis Galton, FRS [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] tcltk crashing R after the (ab)use of tkwait
Running this: library(tcltk) tt - tktoplevel() done - tclVar(0) but - tkbutton(tt, text=OK, command=function() tclvalue(done) - 1) tkpack(but) tkwait.variable(done) works as fine as long as I click the OK. However, if I close the window (by clicking in the X), R enters into an infinite loop and there's no way of returning except by closing the R window. Why? What am I doing wrong? Alberto Monteiro __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] E-Mail/Post Threading (was: Bonferroni p-value greater t
On 29-Mar-07 17:15:27, Marc Schwartz wrote: [...] Just a quick heads up here, that deleting the body text of a message or changing the subject line, does not alter the 'linkage' between posts. There are standards for how messages are 'threaded' and largely have to do with the e-mail headers, not the e-mail content. A couple of quick references that might be helpful: http://people.dsv.su.se/~jpalme/ietf/message-threading.html http://www.jwz.org/doc/threading.html This above, of course, is a good reason for not replying to an existing message when you want to start a completely new thread. However, I'm wondering what is the best way to start a new thread which legitimately branches out from an existing one. For example, someone posts a message which discusses at length a method of isotonic binary regression, and in the middle of this describes a curious approach to obtaining confidence bands for the regression. I'm intrigued by the confidence band issue, get some ideas about it, and want to start a new thread to develop just this aspect. However, to do so I want in the first place to include several quotations from the original message. This, of course, is most easily done by replying to that message -- so that it gets included in the reply -- and editing this included message, and changing the subject. But that stays in the old thread, which I don't want. Now of course one can copy over the old text into a brand new blank message, and edit it up into a simulacrum of a reply -- all the usual On NN March 2007, XXX wrote: ... as well as the inclusion markers, etc.. But that could be tedious. Nevertheless, perhaps it is the right thing to do -- unless there's a work-round using the reply mechanism? Best wishes to all, Ted. E-Mail: (Ted Harding) [EMAIL PROTECTED] Fax-to-email: +44 (0)870 094 0861 Date: 29-Mar-07 Time: 19:37:54 -- XFMail -- __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Tail area of sum of Chi-square variables
The Satterthwaite approximation is surprisingly good, especially in the
most interesting range in the right tail (say 0.9 to 0.999). There is also
another, better, approximation with a power of a chi-squared distribution
that has been used in the survey literature.
However, since it is easy to write down the characteristic function and
perfectly feasible to invert it by numerical integration, we might as well
use the right answer.
-thomas
On Thu, 29 Mar 2007, S Ellison wrote:
I was wondering if there are any R functions that give the tail area
of a sum of chisquare distributions of the type:
a_1 X_1 + a_2 X_2
where a_1 and a_2 are constants and X_1 and X_2 are independent
chi-square variables with different degrees of freedom.
You might also check out Welch and Satterthwaite's (separate) papers on
effective degrees of freedom for compound estimates of variance, which led to
a thing called the welch-satterthwaite equation by one (more or less
notorious, but widely used) document called the ISO Guide to Expression of
Uncertainty in Measurement (ISO, 1995). The original papers are
B. L. Welch, J. Royal Stat. Soc. Suppl.(1936) 3 29-48
B. L. Welch, Biometrika, (1938) 29 350-362
B. L. Welch, Biometrika, (1947) 34 28-35
F. E. Satterthwaite, Psychometrika (1941) 6 309-316
F. E. Satterthwaite, Biometrics Bulletin, (1946) 2 part 6 110-114
The W-S equation - which I believe is a special case of Welch's somewhat more
general treatment - says that if you have multiple independent estimated
variances v[i] (could be more or less equivalent to your a_i X_i?) with
degrees of freedom nu[i], the distribution of their sum is approximately a
scaled chi-squared distribution with effective degrees of freedom
nu.effective given by
nu.effective = sum(v[i])^2 / sum((v[i]^2)/nu[i] )
If I recall correctly, with an observed variance s^2 (corresponding to the
sum(v[i] above if those are observed varianes), nu*(s^2 /sigma^2) is
distributed as chi-squared with degrees of freedom nu, so the scaling factor
for quantiles would come out of there (depending whether you're after the
tail areas for s^2 given sigma^2 or for a confidence interval for sigma^2
given s^2)
However, I will be most interested to see what a more exact calculation
provides!
Steve Ellison
***
This email and any attachments are confidential. Any use, co...{{dropped}}
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Thomas Lumley Assoc. Professor, Biostatistics
[EMAIL PROTECTED] University of Washington, Seattle
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Re: [R] Tail area of sum of Chi-square variables
S Ellison wrote:
I was wondering if there are any R functions that give the tail area
of a sum of chisquare distributions of the type:
a_1 X_1 + a_2 X_2
where a_1 and a_2 are constants and X_1 and X_2 are independent
chi-square variables with different degrees of freedom.
You might also check out Welch and Satterthwaite's (separate) papers on
effective degrees of freedom for compound estimates of variance, which led to
a thing called the welch-satterthwaite equation by one (more or less
notorious, but widely used) document called the ISO Guide to Expression of
Uncertainty in Measurement (ISO, 1995). The original papers are
B. L. Welch, J. Royal Stat. Soc. Suppl.(1936) 3 29-48
B. L. Welch, Biometrika, (1938) 29 350-362
B. L. Welch, Biometrika, (1947) 34 28-35
F. E. Satterthwaite, Psychometrika (1941) 6 309-316
F. E. Satterthwaite, Biometrics Bulletin, (1946) 2 part 6 110-114
The W-S equation - which I believe is a special case of Welch's somewhat more
general treatment - says that if you have multiple independent estimated
variances v[i] (could be more or less equivalent to your a_i X_i?) with
degrees of freedom nu[i], the distribution of their sum is approximately a
scaled chi-squared distribution with effective degrees of freedom
nu.effective given by
nu.effective = sum(v[i])^2 / sum((v[i]^2)/nu[i] )
If I recall correctly, with an observed variance s^2 (corresponding to the
sum(v[i] above if those are observed varianes), nu*(s^2 /sigma^2) is
distributed as chi-squared with degrees of freedom nu, so the scaling factor
for quantiles would come out of there (depending whether you're after the
tail areas for s^2 given sigma^2 or for a confidence interval for sigma^2
given s^2)
However, I will be most interested to see what a more exact calculation
provides!
I believe this is also in Box, 1954, in the guise of sums of squares
under heteroscedsticity and correlation.
@Article{box54ptI,
author = {G. E. P. Box},
title ={Some Theorems on Quadratic Forms Applied in the
Study of Analysis of Variance Problems, I. Effect of
Inequality of Variance in the One-Way
Classification},
journal = {Annals of Mathematical Statistics},
year = 1954,
volume = 25,
number = 2,
pages ={290-302}
}
IIRC (I seem to have temporarily misplaced the actual paper...), there
is a trick by which the characteristic function of a linear combination
of chi-squared variables can be expanded in a (weighted) _sum_ of
chisquare characteristic functions, which gives you an exact expression
for the density and CDF.
Steve Ellison
***
This email and any attachments are confidential. Any use, co...{{dropped}}
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
--
O__ Peter Dalgaard Øster Farimagsgade 5, Entr.B
c/ /'_ --- Dept. of Biostatistics PO Box 2099, 1014 Cph. K
(*) \(*) -- University of Copenhagen Denmark Ph: (+45) 35327918
~~ - ([EMAIL PROTECTED]) FAX: (+45) 35327907
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Re: [R] tcltk crashing R after the (ab)use of tkwait
Alberto Monteiro albmont at centroin.com.br writes: library(tcltk) tt - tktoplevel() done - tclVar(0) but - tkbutton(tt, text=OK, command=function() tclvalue(done) - 1) tkpack(but) tkwait.variable(done) works as fine as long as I click the OK. However, if I close the window (by clicking in the X), R enters into an infinite loop and there's no way of returning except by closing the R window. Works for me with R-2.4.1 on Windows 2000. So better tell us about the details of your operating system. Dieter __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] equivalent datatypes
Duncan Murdoch murdoch at stats.uwo.ca writes: On 3/29/2007 6:45 AM, Schmitt, Corinna wrote: - cell array I don't know what a cell is in C. This is MathLabish. Dieter __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Xemacs, ESS, R config issue
I've searched for 45 minutes, apparently in all the wrong places for a solution to a configuration issue I'm having. When I use Xemacs with ESS running in R-mode, and I type a - character, it autocompletes it to - . How do I disable this annoying feature? Thanks much. [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] tcltk crashing R after the (ab)use of tkwait
Dieter Menne wrote: library(tcltk) tt - tktoplevel() done - tclVar(0) but - tkbutton(tt, text=OK, command=function() tclvalue(done) - 1) tkpack(but) tkwait.variable(done) works as fine as long as I click the OK. However, if I close the window (by clicking in the X), R enters into an infinite loop and there's no way of returning except by closing the R window. Works for me with R-2.4.1 on Windows 2000. So better tell us about the details of your operating system. R 2.4.1 on Windows XP. Should they work differently? Alberto Monteiro __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Regarding Vista
christian.ritter at shell.com writes: The Vista issue is not innocent as it threatens the life of R within large corporations. So any posts on how R runs under Vista and what has to be done to make it work and what cannot be done etc will be very useful. Main problem seems to be the installation of chm-files when upgrading. I had to switch off all security mechanisms to get it done. Which is probably not what you would like to have in a corporate environment. As a temporary workaround, it would probably be best to optionally disable chm installation. Or do a poll if is is required, after all it's considered a legacy format nowadays. Dieter __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] E-Mail/Post Threading (was: Bonferroni p-value greater t
On Thu, 2007-03-29 at 19:38 +0100, [EMAIL PROTECTED] wrote: On 29-Mar-07 17:15:27, Marc Schwartz wrote: [...] Just a quick heads up here, that deleting the body text of a message or changing the subject line, does not alter the 'linkage' between posts. There are standards for how messages are 'threaded' and largely have to do with the e-mail headers, not the e-mail content. A couple of quick references that might be helpful: http://people.dsv.su.se/~jpalme/ietf/message-threading.html http://www.jwz.org/doc/threading.html This above, of course, is a good reason for not replying to an existing message when you want to start a completely new thread. However, I'm wondering what is the best way to start a new thread which legitimately branches out from an existing one. For example, someone posts a message which discusses at length a method of isotonic binary regression, and in the middle of this describes a curious approach to obtaining confidence bands for the regression. I'm intrigued by the confidence band issue, get some ideas about it, and want to start a new thread to develop just this aspect. However, to do so I want in the first place to include several quotations from the original message. This, of course, is most easily done by replying to that message -- so that it gets included in the reply -- and editing this included message, and changing the subject. But that stays in the old thread, which I don't want. Now of course one can copy over the old text into a brand new blank message, and edit it up into a simulacrum of a reply -- all the usual On NN March 2007, XXX wrote: ... as well as the inclusion markers, etc.. But that could be tedious. Nevertheless, perhaps it is the right thing to do -- unless there's a work-round using the reply mechanism? Best wishes to all, Ted. Hi Ted, The general approach, if relatedly digressing (also described in various 'netiquette' guides) is to do what I did here, which is reply to the post in question, but change the subject header by using New Subject (was: Old Subject). This enables you to easily engage in the sort of editing that you describe, and still links your reply back to the original thread, under the presumption that your reply is in some way related to the subject matter of the original thread. Since most e-mail systems (list managers, MUA's, etc.) thread based upon the headers and not the subject, as described in the above references, unless you generate a completely new e-mail, your reply will be linked to the e-mail and thread to which you are replying. It's pretty much a dichotomous situation. Use 'reply' and you get linked to the old thread. Use a 'new' e-mail and you start a new thread. If you are truly moving in a new direction, I would be tempted to start a new thread and perhaps to make it easier for readers, include a reference/link to the post in question. That way, you keep your new e-mail in a separate thread, while 'virtually' linking it back to the original that raised your interest. HTH, Marc __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Wikibooks
As a big fan of Wikipedia, it's frustrating to see how little there is about R in the correlated project, the Wikibooks: http://en.wikibooks.org/wiki/R_Programming Alberto Monteiro __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Xemacs, ESS, R config issue
On Thu, 2007-03-29 at 13:57 -0500, c n wrote: I've searched for 45 minutes, apparently in all the wrong places for a solution to a configuration issue I'm having. When I use Xemacs with ESS running in R-mode, and I type a - character, it autocompletes it to - . How do I disable this annoying feature? Thanks much. Don't know about disabling it, but to get a _, just press it twice. _ doesn't auto-complete in text strings (quoted). _ isn't allowed for assignment anymore, so the only place I can think of at the mo is that you want to type a _ in a variable name? Also, this is best addressed on the ESS mailing list: ess-helpATstatDOTmathDOTethzDOTch (just remove the AT and DOTs) G -- %~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~% Gavin Simpson [t] +44 (0)20 7679 0522 ECRC, UCL Geography, [f] +44 (0)20 7679 0565 Pearson Building, [e] gavin.simpsonATNOSPAMucl.ac.uk Gower Street, London [w] http://www.ucl.ac.uk/~ucfagls/ UK. WC1E 6BT. [w] http://www.freshwaters.org.uk %~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~%~% __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Xemacs, ESS, R config issue
On Thu, 2007-03-29 at 13:57 -0500, c n wrote: I've searched for 45 minutes, apparently in all the wrong places for a solution to a configuration issue I'm having. When I use Xemacs with ESS running in R-mode, and I type a - character, it autocompletes it to - . How do I disable this annoying feature? Thanks much. I think you mean an underscore _ rather than a hyphen -? If you type __ (a double underscore) you will get an underscore. If you want to disable that feature, put the following: (ess-toggle-underscore nil) in your init.el file after the point where ESS is loaded. BTW, there is a dedicated ESS list: https://stat.ethz.ch/mailman/listinfo/ess-help HTH, Marc Schwartz __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Xemacs, ESS, R config issue
c n [EMAIL PROTECTED] writes: When I use Xemacs with ESS running in R-mode, and I type a - character, it autocompletes it to - . How do I disable this annoying feature? From the ESS manual: , |* ESS[S]: Pressing underscore (_) once inserts - (as before); | pressing underscore twice inserts a literal underscore. To stop | this smart behaviour, add (ess-toggle-underscore nil) to your | .emacs after ess-site has been loaded; ` HTH Patrick -- Patrick Drechsler tel: +44 1223 334441 Department of Zoology fax: +44 1223 336687 University of Cambridge Downing Street Cambridge CB2 3EJ, UK __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] E-Mail/Post Threading (was: Bonferroni p-value greater t
On 29-Mar-07 19:21:12, Marc Schwartz wrote: On Thu, 2007-03-29 at 19:38 +0100, [EMAIL PROTECTED] wrote: On 29-Mar-07 17:15:27, Marc Schwartz wrote: [...] Just a quick heads up here, that deleting the body text of a message or changing the subject line, does not alter the 'linkage' between posts. There are standards for how messages are 'threaded' and largely have to do with the e-mail headers, not the e-mail content. A couple of quick references that might be helpful: http://people.dsv.su.se/~jpalme/ietf/message-threading.html http://www.jwz.org/doc/threading.html This above, of course, is a good reason for not replying to an existing message when you want to start a completely new thread. However, I'm wondering what is the best way to start a new thread which legitimately branches out from an existing one. For example, someone posts a message which discusses at length a method of isotonic binary regression, and in the middle of this describes a curious approach to obtaining confidence bands for the regression. I'm intrigued by the confidence band issue, get some ideas about it, and want to start a new thread to develop just this aspect. However, to do so I want in the first place to include several quotations from the original message. This, of course, is most easily done by replying to that message -- so that it gets included in the reply -- and editing this included message, and changing the subject. But that stays in the old thread, which I don't want. Now of course one can copy over the old text into a brand new blank message, and edit it up into a simulacrum of a reply -- all the usual On NN March 2007, XXX wrote: ... as well as the inclusion markers, etc.. But that could be tedious. Nevertheless, perhaps it is the right thing to do -- unless there's a work-round using the reply mechanism? Best wishes to all, Ted. Hi Ted, The general approach, if relatedly digressing (also described in various 'netiquette' guides) is to do what I did here, which is reply to the post in question, but change the subject header by using New Subject (was: Old Subject). This enables you to easily engage in the sort of editing that you describe, and still links your reply back to the original thread, under the presumption that your reply is in some way related to the subject matter of the original thread. Since most e-mail systems (list managers, MUA's, etc.) thread based upon the headers and not the subject, as described in the above references, unless you generate a completely new e-mail, your reply will be linked to the e-mail and thread to which you are replying. It's pretty much a dichotomous situation. Use 'reply' and you get linked to the old thread. Use a 'new' e-mail and you start a new thread. If you are truly moving in a new direction, I would be tempted to start a new thread and perhaps to make it easier for readers, include a reference/link to the post in question. That way, you keep your new e-mail in a separate thread, while 'virtually' linking it back to the original that raised your interest. HTH, Marc Thanks for the clarification, Marc. Nicely put. Now that I visit the R-help archives website, I can see that these subthreads get hung off the originals in that display (just as out present subthread is, as seen there), which is a good way for it to happen (and ideally suited to the sort of situation which I described). And the way the subject was changed keeps it nice and clear as to what happened. Best wishes, Ted. E-Mail: (Ted Harding) [EMAIL PROTECTED] Fax-to-email: +44 (0)870 094 0861 Date: 29-Mar-07 Time: 21:39:17 -- XFMail -- __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] pipe Apple
This expression, read.table(pipe(pbpaste)) does work for me on an OS X 10.4.9 system. And it was working 2 years ago on a 10.3.8 system (an older R, obviously). I would look to how R was installed, what version of R, that kind of thing. Use the sessionInfo() command to provide that information. (the posting guide asks for information about the R version, without which it is more difficult to help) What does the R expression capabilities() return? Also, if what she's copying and pasting from is Excel, the gdata package has a function read.xls() function which can read data directly from Excel. -Don At 12:39 PM -0500 3/29/07, A. Beaujean wrote: Hi, I have a student trying to run R on an Apple (OS 10.3.9). She tried to cut-and-paste the data via the code: data-read.table(pipe(pbpaste)) But she keeps getting the error message: 'error in pipe(pbpaste): pipe connections are not available on this system' I do not know much about using an Apple. Has anyone run into this before? Does anyone have any ideas for how to fix the problem? Thanks! Alex -- *** A. Alexander Beaujean, Ph.D., LSSP Licensed Psychologist (Provisional, TX) http://myprofile.cos.com/abeaujean http://www.baylor.edu/soe/faculty/index.php?id=38476 General impressions are never to be trusted. Unfortunately when they are of long standing they become fixed rules of life, and assume a prescriptive right not to be questioned. Consequently those who are not accustomed to original inquiry entertain a hatred and a horror of statistics. They cannot endure the idea of submitting their sacred impressions to cold-blooded verification. But it is the triumph of scientific men to rise superior to such superstitions, to devise tests by which the value of beliefs may be ascertained, and to feel sufficiently masters of themselves to discard contemptuously whatever may be found untrue. --Sir Francis Galton, FRS [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- -- Don MacQueen Environmental Protection Department Lawrence Livermore National Laboratory Livermore, CA, USA __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] E-Mail/Post Threading (was: Bonferroni p-value greater t
On Mar 29, 2007, at 3:21 PM, Marc Schwartz wrote: Since most e-mail systems (list managers, MUA's, etc.) thread based upon the headers and not the subject, as described in the above references, unless you generate a completely new e-mail, your reply will be linked to the e-mail and thread to which you are replying. It's pretty much a dichotomous situation. Use 'reply' and you get linked to the old thread. Use a 'new' e-mail and you start a new thread. If you are truly moving in a new direction, I would be tempted to start a new thread and perhaps to make it easier for readers, include a reference/link to the post in question. That way, you keep your new e-mail in a separate thread, while 'virtually' linking it back to the original that raised your interest. Perhaps moving a bit off topic here, but to elaborate a bit more on this: Each thread is really a tree, where your message is a child of the message you responded to. Since typically each person responds to the last message in the thread, this often ends up being linear. But if for instance three people respond to the same original message, this creates three children of the root node. You can see this in action here for instance: http://news.gmane.org/ gmane.emacs.ess.general It then depends on your software, how to show this tree. Most mail clients would just flatten it out into a single list, which is what we usually refer to as a thread I guess. But the richer structure is there. So based on this I would suggest simply responding to the message you want to, changing the subject appropriately. HTH, Marc Haris Skiadas Department of Mathematics and Computer Science Hanover College __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Using functions in LAPACK in a C program
Hi, I wonder where I can find an example of using a function in LAPACK library in a user's own C code. I wrote a C program which will be compiled and linked to produce a DLL file and then loaded into R. I hope to use a function from LAPACK library, for example, dgesdd, in the program. Following R manual, I call the function by F77_CALL(dgesdd) in the program. The program can be compiled without problems. However, when it is linked to produce a DLL file, I get an error message Test.obj : error LNK2001: unresolved external symbol _dgesdd_ Test.dll : fatal error LNK1120: 1 unresolved externals I use VC++6.0 and the command of linking is something like this link.exe Rdll.lib /nologo /dll /out:Test.dll /libpath:C:\R\R-2.2.1\src\gnuwin32 Test.obj Apparently, the linker cannot resolve dgesdd from Rdll.lib. If anyone knows what I missed here or any example that shows how this can be done properly, please let me know. Thanks a lot. Paul. Never miss an email again! __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Wikibooks
Alberto Monteiro albmont at centroin.com.br writes: As a big fan of Wikipedia, it's frustrating to see how little there is about R in the correlated project, the Wikibooks: http://en.wikibooks.org/wiki/R_Programming Alberto Monteiro Well, we do have an R wiki -- http://wiki.r-project.org/rwiki/doku.php -- although it is not as active as I'd like. (We got stuck halfway through porting Paul Johnson's R Tips to it ...) Please contribute! Most of the (considerable) effort people expend in answering questions about R goes to the mailing lists -- I personally would like it if some tiny fraction of that energy could be redirected toward the wiki, where information can be presented in a nicer format and (ideally) polished over time -- rather than having to dig back through multiple threads on the mailing lists to get answers. (After that we have to get people to look for the answers on the wiki.) Just my two cents -- and I've been delinquent in my wiki'ing recently too ... Ben Bolker __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] [HH] extending ancova function for 2 factors
Hi, what would be a good way of enhancing the ancova function from the HH package when using a 2 factor ANCOVA? The current behaviour for the ancova function from package HH is: -- | P1 || P1 || P3 || P4 | | PS | - the lattice strip -- | x||x ||x ||x | | | | x ||x || x|| x | |superimp.| - the lattice plot |x || x || x ||x | | | -- P1:P4 : Show an xy-plot for each factor level of the covariate P. PS: Displays the previous plots superimposed superimp: P1:P4 superimposed I would like to use this function for a two factor design. - | Q1 || Q1 || Q1 || Q1 | | PS.Pi | - strip1 - | P1 || P1 || P3 || P4 | | PS.Pi | - strip2 - |x || x || x ||x | || |x || x || x ||x | || - plot |x || x || x ||x | || - - | Q2 || Q2 || Q2 || Q2 | | PS.Pi | - strip1 - | P1 || P1 || P3 || P4 | | PS.Pi | - strip2 - |x || x || x ||x | || |x || x || x ||x | || - plot |x || x || x ||x | || - [...] - | Q5 || Q5 || Q5 || Q5 | | PS.Pi | - strip1 - | P1 || P1 || P3 || P4 | | PS.Pi | - strip2 - |x || x || x ||x | || |x || x || x ||x | || - plot |x || x || x ||x | || - Here is an example: --8---cut here---start-8--- rm(list = ls(all = TRUE)) rm(list = c(ls())) library(lattice) library(HH) ## 1. generate data random - rnorm(200) y - abs(random) x1.cont - abs(random) x2.fac - as.factor(rep(1:5, 4)) # 4 groups x3.fac - as.factor(rep(1:4, each=5))# 5 groups A - data.frame(y, x1.cont, x2.fac, x2.fac) ## 2. plot trellis plot: foo - xyplot(log(y) ~ log(x1.cont) | x2.fac * x3.fac, data = A, type = c(p,r), strip = strip.custom(strip.names=TRUE), as.table=TRUE) plot(foo) ## 3. plot ancova plot using HH: ## normal usage: ancova(y ~ x1.cont * x2.fac) ## 4. Trying to combine ancova with trellis: ## does not work: ancova(y ~ x1.cont * x2.fac * x3.fac) --8---cut here---end---8--- -- Patrick Drechsler Department of Zoology University of Cambridge Downing Street Cambridge CB2 3EJ, UK __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] ccf time units
Hi, I am using ccf but I could not figure out how to calculate the actual lag in number of periods from the returned results. The documentation for ccf says:The lag is returned and plotted in units of time. What does units of time mean? For example: x=ldeaths x1=lag(ldeaths,1) results=ccf(x,x1) results Autocorrelations of series 'X', by lag -1.2500 -1.1667 -1.0833 -1. -0.9167 -0.8333 -0.7500 -0.6667 -0.5833 - 0.5000 -0.297 0.011 0.380 0.651 0.738 0.664 0.392 -0.011 -0.383 - 0.618 -0.4167 -0. -0.2500 -0.1667 -0.0833 0. 0.0833 0.1667 0.2500 0. -0.693 -0.619 -0.362 0.020 0.405 0.770 0.981 0.749 0.376 - 0.004 0.4167 0.5000 0.5833 0.6667 0.7500 0.8333 0.9167 1. 1.0833 1.1667 -0.366 -0.610 -0.686 -0.602 -0.368 -0.012 0.388 0.650 0.705 0.614 1.2500 0.341 I see that at time unit 0.0833, the correlation is close to 1. But how do I know time unit 0.0833 is actually lag 1? Is there a function to do the conversion? Thanks, Tom [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] ccf time units
The unit of time for a ts class object is deltat(ldeaths). See the ?deltat help page. On 3/29/07, tom soyer [EMAIL PROTECTED] wrote: Hi, I am using ccf but I could not figure out how to calculate the actual lag in number of periods from the returned results. The documentation for ccf says:The lag is returned and plotted in units of time. What does units of time mean? For example: x=ldeaths x1=lag(ldeaths,1) results=ccf(x,x1) results Autocorrelations of series 'X', by lag -1.2500 -1.1667 -1.0833 -1. -0.9167 -0.8333 -0.7500 -0.6667 -0.5833 - 0.5000 -0.297 0.011 0.380 0.651 0.738 0.664 0.392 -0.011 -0.383 - 0.618 -0.4167 -0. -0.2500 -0.1667 -0.0833 0. 0.0833 0.1667 0.2500 0. -0.693 -0.619 -0.362 0.020 0.405 0.770 0.981 0.749 0.376 - 0.004 0.4167 0.5000 0.5833 0.6667 0.7500 0.8333 0.9167 1. 1.0833 1.1667 -0.366 -0.610 -0.686 -0.602 -0.368 -0.012 0.388 0.650 0.705 0.614 1.2500 0.341 I see that at time unit 0.0833, the correlation is close to 1. But how do I know time unit 0.0833 is actually lag 1? Is there a function to do the conversion? Thanks, Tom [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Vector indexing question
Suppose you have 4 related vectors: a.id-c(1:25, 1:25, 1:25) a.vals - c(101:175)# same length as a.id (the values for those IDs) a.id.levels - c(1:25) a.id.ratings - rep(letters[1:5], times=5)# same length as a.id.levels What I would like to do is specify a rating from a.ratings (e.g. e), get the vector of corresponding IDs from a.id.levels (via a.id.levels[a.id.ratings=='e']) and then somehow use those IDs in a.id to get the corresponding values from a.vals. I think I can probably write a loop to construct of a vector of ratings of the same length as a.id so that the ratings match the ID, and then go from there. Is there a better way? Perhaps using factors or levels or something? Thanks, --Paul -- Paul Lynch Aquilent, Inc. National Library of Medicine (Contractor) __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Wikibooks
I think sometime ago someone suggested that we append a comments/discussion/wiki section to the end of every R functions' help page that is editable by everyday users. In other words, every R function help page has a fixed component that has met R-core's approval and a clearly marked and more flexible components by everyday users. The comments section on every function could contain suggestions, warnings (e.g. the use of c versus as.vector thread that was discussed today), examples, do's and don'ts, suggestion for clarification in documents. I think starting from function-level is an interesting idea to complement Paul Johnson's R tips. This comments could perhaps be cleaned up and integrated for future releases if the R-core agrees on its usefulness. Think of as a Bayesian approach for maintaining information. Regards, Adai Frank E Harrell Jr wrote: Ben Bolker wrote: Alberto Monteiro albmont at centroin.com.br writes: As a big fan of Wikipedia, it's frustrating to see how little there is about R in the correlated project, the Wikibooks: http://en.wikibooks.org/wiki/R_Programming Alberto Monteiro Well, we do have an R wiki -- http://wiki.r-project.org/rwiki/doku.php -- although it is not as active as I'd like. (We got stuck halfway through porting Paul Johnson's R Tips to it ...) Please contribute! Most of the (considerable) effort people expend in answering questions about R goes to the mailing lists -- I personally would like it if some tiny fraction of that energy could be redirected toward the wiki, where information can be presented in a nicer format and (ideally) polished over time -- rather than having to dig back through multiple threads on the mailing lists to get answers. (After that we have to get people to look for the answers on the wiki.) I would like to strongly second Ben. In some ways, R experts are too nice. Continuing to answer the same questions over and over does not lead to a better way using R wiki. I would rather see the work go into enhancing the wiki and refactoring information, and responses to many r-help please for help be see wiki topic x. While doing this let's consider putting a little more burden on new users to look for good answers already provided. Frank Just my two cents -- and I've been delinquent in my wiki'ing recently too ... Ben Bolker __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] Using Java or Tcl/Tk in R
Dear R People: This is more of an opinion question please: When putting together GUI type functions, is it better to use JAVA or Tcl/Tk, please? Any input is appreciated! Sincerely, Erin Hodgess Associate Professor Department of Computer and Mathematical Sciences University of Houston - Downtown mailto: [EMAIL PROTECTED] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Wikibooks
Question: Many (perhaps most?) questions on the list are easily answerable simply by checking existing R Docs (Help file/man pages, Intro to R, etc.). Why would a Wiki be more effective in deflecting such questions from the mailing list than them? Why would too helpful R experts be more inclined to refer people to the Wiki than the existing docs? Bottom line: it's psychology at issue here, I think, not the form of the docs. Disclaimer 1: None of this is meant to reflect one way or ther other on the usefulness of Wikis as a documentation format -- only their ability to change the Help list culture. Disclaimer 2: Others have repeatedly made similar comments (asking us to refer people to the docs rather than providing explicit answers, I mean). Cheers, Bert Gunter Genentech Nonclinical Statistics South San Francisco, CA 94404 650-467-7374 -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Frank E Harrell Jr Sent: Thursday, March 29, 2007 3:32 PM To: Ben Bolker Cc: r-help@stat.math.ethz.ch Subject: Re: [R] Wikibooks Ben Bolker wrote: Alberto Monteiro albmont at centroin.com.br writes: As a big fan of Wikipedia, it's frustrating to see how little there is about R in the correlated project, the Wikibooks: http://en.wikibooks.org/wiki/R_Programming Alberto Monteiro Well, we do have an R wiki -- http://wiki.r-project.org/rwiki/doku.php -- although it is not as active as I'd like. (We got stuck halfway through porting Paul Johnson's R Tips to it ...) Please contribute! Most of the (considerable) effort people expend in answering questions about R goes to the mailing lists -- I personally would like it if some tiny fraction of that energy could be redirected toward the wiki, where information can be presented in a nicer format and (ideally) polished over time -- rather than having to dig back through multiple threads on the mailing lists to get answers. (After that we have to get people to look for the answers on the wiki.) I would like to strongly second Ben. In some ways, R experts are too nice. Continuing to answer the same questions over and over does not lead to a better way using R wiki. I would rather see the work go into enhancing the wiki and refactoring information, and responses to many r-help please for help be see wiki topic x. While doing this let's consider putting a little more burden on new users to look for good answers already provided. Frank Just my two cents -- and I've been delinquent in my wiki'ing recently too ... Ben Bolker __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. -- Frank E Harrell Jr Professor and Chair School of Medicine Department of Biostatistics Vanderbilt University __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Vector indexing question
Sounds like you have two different tables and are trying to mine one based on the other. Try ref - data.frame( levels = 1:25, ratings = rep(letters[1:5], times=5) ) db - data.frame( vals=101:175, levels=c(1:25, 1:25, 1:25) ) levels.of.interest - ref$levels[ ref$rating==a ] db$vals[ which(db$levels %in% levels.of.interest) ] [1] 101 106 111 116 121 126 131 136 141 146 151 156 161 166 171 OR a much more intuitive way is to merge both tables and proceeding as out - merge( db, ref, by=levels, all.x=TRUE ) out - out[ order(out$val), ] # little cleanup subset( out, ratings==a ) # ignore the rownames levels vals ratings 1 1 101 a 16 6 106 a 31 11 111 a 46 16 116 a 61 21 121 a 3 1 126 a 17 6 131 a 32 11 136 a 47 16 141 a 62 21 146 a 2 1 151 a 18 6 156 a 33 11 161 a 48 16 166 a 63 21 171 a Then you can do cool things using the apply() family like tapply( out$vals, out$ratings, mean ) a b c d e 136 137 138 139 140 Check out %in%, merge and apply. Regards, Adai Paul Lynch wrote: Suppose you have 4 related vectors: a.id-c(1:25, 1:25, 1:25) a.vals - c(101:175)# same length as a.id (the values for those IDs) a.id.levels - c(1:25) a.id.ratings - rep(letters[1:5], times=5)# same length as a.id.levels What I would like to do is specify a rating from a.ratings (e.g. e), get the vector of corresponding IDs from a.id.levels (via a.id.levels[a.id.ratings=='e']) and then somehow use those IDs in a.id to get the corresponding values from a.vals. I think I can probably write a loop to construct of a vector of ratings of the same length as a.id so that the ratings match the ID, and then go from there. Is there a better way? Perhaps using factors or levels or something? Thanks, --Paul __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Wikibooks
Many (perhaps most?) questions on the list are easily answerable simply by checking existing R Docs (Help file/man pages, Intro to R, etc.). Why would a Wiki be more effective in deflecting such questions from the mailing list than them? Why would too helpful R experts be more inclined to refer people to the Wiki than the existing docs? Bottom line: it's psychology at issue here, I think, not the form of the docs. I agree - and there's also a problem that until the wiki becomes useful there's no point referring people to it, and because no one visits it, it doesn't get better. http://www.wikipatterns.com provides some good advice for getting a wiki going. Hadley __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Vector indexing question
On Thu, 2007-03-29 at 19:55 -0400, Paul Lynch wrote: Suppose you have 4 related vectors: a.id-c(1:25, 1:25, 1:25) a.vals - c(101:175)# same length as a.id (the values for those IDs) a.id.levels - c(1:25) a.id.ratings - rep(letters[1:5], times=5)# same length as a.id.levels What I would like to do is specify a rating from a.ratings (e.g. e), get the vector of corresponding IDs from a.id.levels (via a.id.levels[a.id.ratings=='e']) and then somehow use those IDs in a.id to get the corresponding values from a.vals. I think I can probably write a loop to construct of a vector of ratings of the same length as a.id so that the ratings match the ID, and then go from there. Is there a better way? Perhaps using factors or levels or something? Thanks, --Paul Is this what you want? DF - data.frame(a.id, a.vals, a.id.levels, a.id.ratings) DF[DF$a.id.ratings == e, a.vals] [1] 105 110 115 120 125 130 135 140 145 150 155 160 165 170 175 or subset(DF, a.id.ratings == e, select = a.vals) a.vals 5 105 10110 15115 20120 25125 30130 35135 40140 45145 50150 55155 60160 65165 70170 75175 See ?subset HTH, Marc Schwartz __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Wikibooks
I think we occasionally think that it is very easy to get information because
we know how to find the information. This does not mean that other people know
how to find the answer. It is for this reason that questions appear on the
listserver that we might think could be easily found from other sources.
John
John Sorkin M.D., Ph.D.
Chief, Biostatistics and Informatics
Baltimore VA Medical Center GRECC,
University of Maryland School of Medicine Claude D. Pepper OAIC,
University of Maryland Clinical Nutrition Research Unit, and
Baltimore VA Center Stroke of Excellence
University of Maryland School of Medicine
Division of Gerontology
Baltimore VA Medical Center
10 North Greene Street
GRECC (BT/18/GR)
Baltimore, MD 21201-1524
(Phone) 410-605-7119
(Fax) 410-605-7913 (Please call phone number above prior to faxing)
[EMAIL PROTECTED]
hadley wickham [EMAIL PROTECTED] 3/29/2007 7:47 PM
Many (perhaps most?) questions on the list are easily answerable simply by
checking existing R Docs (Help file/man pages, Intro to R, etc.). Why would
a Wiki be more effective in deflecting such questions from the mailing list
than them? Why would too helpful R experts be more inclined to refer people
to the Wiki than the existing docs? Bottom line: it's psychology at issue
here, I think, not the form of the docs.
I agree - and there's also a problem that until the wiki becomes
useful there's no point referring people to it, and because no one
visits it, it doesn't get better.
http://www.wikipatterns.com provides some good advice for getting a wiki going.
Hadley
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Confidentiality Statement:
This email message, including any attachments, is for the so...{{dropped}}
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Re: [R] Using Java or Tcl/Tk in R
It really depends on what you're trying to do. tcl/tk is convenient in that support for it is included with R. There won't be any distribution complications. Obviously, Java is fairly widespread, but then there's the complication of installing rJava or some other R-Java binding. If you're doing anything beyond the most trivial GUI, I would recommend the excellent gWidgets package from John Verzani. It's available from CRAN and provides a simple API for creating widgets from R. gWidgets supports multiple widget library back-ends. Currently, I think there are only backends for GTK+ (via RGtk2) and Java (swing). The RGtk2 backend is the most mature right now. GTK+ is a cross-platform and full-featured widget library. In my opinion it's API is more convenient for most uses than that of Swing, and GTK+ has more features than tcl/tk. gWidgets allows you to prototype your GUI using a simple API without depending on a specific toolkit. Once your application matures to the point that it requires features that are not within the scope of the simple gWidgets API, you can make the decision about moving to a specific toolkit. I hope this helps, Michael On 3/29/07, Erin Hodgess [EMAIL PROTECTED] wrote: Dear R People: This is more of an opinion question please: When putting together GUI type functions, is it better to use JAVA or Tcl/Tk, please? Any input is appreciated! Sincerely, Erin Hodgess Associate Professor Department of Computer and Mathematical Sciences University of Houston - Downtown mailto: [EMAIL PROTECTED] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] problem using mcmcsamp() with glmer models containing interaction terms in fixed effects
Dear All,
I've been using mcmcsamp() successfully with a few different mixed models
but I can't get it to work with the following. Is there an obvious reason
why it shouldn't work with a model of this structure ?
*brief summary of objective:
I want to test the effect of no-fishing marine reserves on the abundance of
a target species.
I have samples at coral reef sites inside and outside of reserves, from
visits before and after the establishment of the reserves. Samples are
counts of the target species.
I plan to test this by looking at the interaction between reserve zone
(green/blue, green means no-fishing allowed) and the change in abundance
between the before sample (visit 0), and after sample (visit 1). -- please
say if you think there is a better way.
Samples come from several different regions, thus it would be nice to be
able to model differences between regions in the response to no-fishing and
to expand possible inference beyond this sample of regions.
My problem is getting a test for the fixed effects, see
http://wiki.r-project.org/rwiki/doku.php?id=guides:lmer-tests for background
on why I want to use mcmcsamp.
Thank you for your attention,
Andrew Dolman - Australian Institute of Marine Science.
--
[EMAIL PROTECTED]
[EMAIL PROTECTED]
# required packages
library('lme4')
# some dummy data
counts - c(rpois(75, 2), rpois(25,4)) # number of fish in a sample
[dependent variable - poisson distributed]
visit - c(rep(0, 50), rep(1,50)) # sample visit number, 0 or 1 to indicate
pre and post no-fishing reserve establishment
zone - as.factor(rep(c(rep(blue, 25), rep(green,25)),2)) #
inside/outside no-fishing reserve
region - as.factor(rep(c(island1, island2),50)) # spatial grouping
factor
data1 - data.frame(counts, visit, zone, region)
rm (counts, visit, zone, region)
# a quick look
bwplot(I(sqrt(counts))~as.factor(visit)|region, data=data1)
# two lmer models
lmer1 - lmer (counts~visit+visit:zone + (1|region), data=data1,
family=poisson(link=log))
lmer2 - lmer (counts~visit+visit:zone + (visit+visit:zone|region),
data=data1, family=poisson(link=log))
mcmc1 - mcmcsamp(lmer1, n=1) # works
mcmc2 - mcmcsamp(lmer2, n=1) # doesn't work
[[alternative HTML version deleted]]
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Re: [R] on hazardous
Ground floor to the future Critical Care New SYm-C.C.T.I 16 Cents is a STEAL This could hit in short and over in the long run This one is Guaranteed to double in next 2 days Get in this gem tomorrow, Catch an easy doubler!! their fourth straight win, a 131-107 blowout of the Phoenix Suns on Saturday have the regroup a little bit.'' Denver has struggled all season to get any But we didn't make the NCAA tournament and that was the goal. To that extent, defense. ''That team can blow you out and they can score in bunches,'' he said - Original Message - From: YMarguerite FFarr [EMAIL PROTECTED] To: [EMAIL PROTECTED] Sent: Thursday, March 22, 2007 8:27 PM Subject: on hazardous Ground floor to the future Critical Care New SYm-C.C.T.I 16 Cents is a STEAL This could hit in short and over in the long run __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Vector indexing question
On Thu, 29 Mar 2007, Paul Lynch wrote: Suppose you have 4 related vectors: a.id-c(1:25, 1:25, 1:25) a.vals - c(101:175)# same length as a.id (the values for those IDs) a.id.levels - c(1:25) a.id.ratings - rep(letters[1:5], times=5)# same length as a.id.levels What I would like to do is specify a rating from a.ratings (e.g. e), get the vector of corresponding IDs from a.id.levels (via a.id.levels[a.id.ratings=='e']) and then somehow use those IDs in a.id to get the corresponding values from a.vals. see ?factor ?match ( in case a.id.levels does not actually index a.id.ratings) ?split a.ratings.factor - factor( a.id.ratings[ match(a.id, a.id.levels) ]) a.vals[ a.ratings.factor == 'e' ] [1] 105 110 115 120 125 130 135 140 145 150 155 160 165 170 175 split( a.vals, a.ratings.factor ) # more generally $a [1] 101 106 111 116 121 126 131 136 141 146 151 156 161 166 171 $b [1] 102 107 112 117 122 127 132 137 142 147 152 157 162 167 172 [output truncated] lm( a.vals ~ a.ratings.factor - 1 ) # means of a.vals Call: lm(formula = a.vals ~ a.ratings.factor - 1) Coefficients: a.ratings.factora a.ratings.factorb a.ratings.factorc a.ratings.factord a.ratings.factore 136137138139 140 I think I can probably write a loop to construct of a vector of ratings of the same length as a.id so that the ratings match the ID, and then go from there. Is there a better way? Perhaps using factors or levels or something? A warning: using factor() in this way a.ratings.factor - factor( a.id, levels=a.id.levels, labels=a.id.ratings ) will work in this case: a.vals[ a.ratings.factor == 'e' ] but generally will get you into trouble as its creates a factor with 25 non-unique levels. So, split( a.vals, a.ratings.factor ) ends up giving a list of 25 (non-uniquely labelled) components HTH, Chuck Thanks, --Paul -- Paul Lynch Aquilent, Inc. National Library of Medicine (Contractor) __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. Charles C. Berry(858) 534-2098 Dept of Family/Preventive Medicine E mailto:[EMAIL PROTECTED] UC San Diego http://biostat.ucsd.edu/~cberry/ La Jolla, San Diego 92093-0901 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Vector indexing question
Adai-- Thanks a lot! This is just what I was looking for. I was almost sure there had to be a neat of doing this. Bert-- Thanks for the tip. Marc-- Not quite, although your solution works fine for the case I gave. What I had in mind for a.id was an arbitrary sequence of the numbers in the range [1,25], of length 75, though I was not savvy enough with R to express that succinctly. You spotted a shortcut that I hadn't reallized I was introducing. Thanks all for your help! --Paul On 3/29/07, Adaikalavan Ramasamy [EMAIL PROTECTED] wrote: Sounds like you have two different tables and are trying to mine one based on the other. Try ref - data.frame( levels = 1:25, ratings = rep(letters[1:5], times=5) ) db - data.frame( vals=101:175, levels=c(1:25, 1:25, 1:25) ) levels.of.interest - ref$levels[ ref$rating==a ] db$vals[ which(db$levels %in% levels.of.interest) ] [1] 101 106 111 116 121 126 131 136 141 146 151 156 161 166 171 OR a much more intuitive way is to merge both tables and proceeding as out - merge( db, ref, by=levels, all.x=TRUE ) out - out[ order(out$val), ] # little cleanup subset( out, ratings==a ) # ignore the rownames levels vals ratings 1 1 101 a 16 6 106 a 31 11 111 a 46 16 116 a 61 21 121 a 3 1 126 a 17 6 131 a 32 11 136 a 47 16 141 a 62 21 146 a 2 1 151 a 18 6 156 a 33 11 161 a 48 16 166 a 63 21 171 a Then you can do cool things using the apply() family like tapply( out$vals, out$ratings, mean ) a b c d e 136 137 138 139 140 Check out %in%, merge and apply. Regards, Adai Paul Lynch wrote: Suppose you have 4 related vectors: a.id-c(1:25, 1:25, 1:25) a.vals - c(101:175)# same length as a.id (the values for those IDs) a.id.levels - c(1:25) a.id.ratings - rep(letters[1:5], times=5)# same length as a.id.levels What I would like to do is specify a rating from a.ratings (e.g. e), get the vector of corresponding IDs from a.id.levels (via a.id.levels[a.id.ratings=='e']) and then somehow use those IDs in a.id to get the corresponding values from a.vals. I think I can probably write a loop to construct of a vector of ratings of the same length as a.id so that the ratings match the ID, and then go from there. Is there a better way? Perhaps using factors or levels or something? Thanks, --Paul -- Paul Lynch Aquilent, Inc. National Library of Medicine (Contractor) __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Regarding Vista
Hi Dieter,
I am facing the same problem in my case. R 2.4.1 have installed
successfully, but when i try to install the packages from a local zip
file. It gives the following error message. Please tell me how to install
the packages in a corporate environment. I mean i could not understand
your reply, may you be a bit more elaborate so that i can fix up the
problem in my corporate laptop.]
Thanks in advance
-gaurav
Dieter Menne [EMAIL PROTECTED]
Sent by: [EMAIL PROTECTED]
30-03-07 12:32 AM
To
r-help@stat.math.ethz.ch
cc
Subject
Re: [R] Regarding Vista
christian.ritter at shell.com writes:
The Vista issue is not innocent as it threatens the life of R within
large
corporations. So any posts on how R
runs under Vista and what has to be done to make it work and what cannot
be
done etc will be very useful.
Main problem seems to be the installation of chm-files when upgrading. I
had to
switch off all security mechanisms to get it done. Which is probably not
what
you would like to have in a corporate environment.
As a temporary workaround, it would probably be best to optionally disable
chm
installation. Or do a poll if is is required, after all it's considered a
legacy
format nowadays.
Dieter
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide
http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
DISCLAIMER AND CONFIDENTIALITY CAUTION:\ \ This message and ...{{dropped}}
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Re: [R] Using functions in LAPACK in a C program
On Thu, 29 Mar 2007, Paul August wrote: Hi, I wonder where I can find an example of using a function in LAPACK library in a user's own C code. In about 20 R packages, e.g. the recommended package mgcv. I wrote a C program which will be compiled and linked to produce a DLL file and then loaded into R. I hope to use a function from LAPACK library, for example, dgesdd, in the program. Following R manual, I call the function by F77_CALL(dgesdd) in the program. The program can be compiled without problems. However, when it is linked to produce a DLL file, I get an error message Test.obj : error LNK2001: unresolved external symbol _dgesdd_ Test.dll : fatal error LNK1120: 1 unresolved externals I use VC++6.0 and the command of linking is something like this link.exe Rdll.lib /nologo /dll /out:Test.dll /libpath:C:\R\R-2.2.1\src\gnuwin32 Test.obj Apparently, the linker cannot resolve dgesdd from Rdll.lib. If anyone knows what I missed here or any example that shows how this can be done properly, please let me know. Thanks a lot. It is in Rlapack.dll not R.dll. The linking information is in 'Writing R Extensions' for those using the recommended compilation system (search for LAPACK_LIBS). You will need to build an import library for Rlapack.dll and link against that. And BTW you seem to be using R 2.2.1: please update as we can only offer accurate advice on recent systems. -- 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 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] Regarding Vista
*Sorry for duplicate post - i forgot to tell the error
Hi Dieter,
I am facing the same problem in my case. R 2.4.1 have installed
successfully, but when i try to install the packages from a local zip
file. It gives the following error message.
+++
utils:::menuInstallLocal()
Error in zip.unpack(pkg, tmpDir) : cannot open file 'C:/Program
Files/R/R-2.4.1/library/file5d2b5841/aaMI/chtml/aaMI.chm'
+++
Please tell me how to install the packages in a corporate environment. I
mean i could not understand your reply, may you be a bit more elaborate so
that i can fix up the problem in my corporate laptop.
Thanks in advance
-gaurav
Dieter Menne [EMAIL PROTECTED]
Sent by: [EMAIL PROTECTED]
30-03-07 12:32 AM
To
r-help@stat.math.ethz.ch
cc
Subject
Re: [R] Regarding Vista
christian.ritter at shell.com writes:
The Vista issue is not innocent as it threatens the life of R within
large
corporations. So any posts on how R
runs under Vista and what has to be done to make it work and what cannot
be
done etc will be very useful.
Main problem seems to be the installation of chm-files when upgrading. I
had to
switch off all security mechanisms to get it done. Which is probably not
what
you would like to have in a corporate environment.
As a temporary workaround, it would probably be best to optionally disable
chm
installation. Or do a poll if is is required, after all it's considered a
legacy
format nowadays.
Dieter
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide
http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
DISCLAIMER AND CONFIDENTIALITY CAUTION:\ \ This message and ...{{dropped}}
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
