Re: [R] Error producing density curve

2008-08-26 Thread Nicky Chorley
2008/8/27 Nicky Chorley <[EMAIL PROTECTED]>: > 2008/8/27 rr400 <[EMAIL PROTECTED]>: >> >> Hi, i have never really used R before and i need to produce a density curve >> for use in an assignment. Following the instructions in the manual provided >> with my course i keep getting this error message: >

Re: [R] Finding a probability

2008-08-26 Thread Moshe Olshansky
You commands are correct and the interpretation is that the probability that a normal random variable with mean 1454.190 and standard deviation 162.6301 achieves a value of 417 or less is 8.99413e-11 --- On Wed, 27/8/08, rr400 <[EMAIL PROTECTED]> wrote: > From: rr400 <[EMAIL PROTECTED]> > Subje

[R] Converting 1-D array to vector

2008-08-26 Thread Ronnen Levinson
Hi. How do I convert a one-dimensional array of characters to a character vector? In the example below I am trying to get the result c("a","d"). The function as.vector() returns the same one-dimensional array, and unlist() returns something more complicated than I seek. Yours tr

Re: [R] Error producing density curve

2008-08-26 Thread Nicky Chorley
2008/8/27 rr400 <[EMAIL PROTECTED]>: > > Hi, i have never really used R before and i need to produce a density curve > for use in an assignment. Following the instructions in the manual provided > with my course i keep getting this error message: > "Error in plot.xy(xy, type, ...) : invalid plot ty

[R] Finding a probability

2008-08-26 Thread rr400
Hi, i am trying to determine a certain probability and i am unsure if the commands i have entered into R are correct. I am trying to determine how unusual it would be to find something with the value 417 for a set of numbers with mean 1454.190 and standard deviation 162.6301. The command i entere

[R] Error producing density curve

2008-08-26 Thread rr400
Hi, i have never really used R before and i need to produce a density curve for use in an assignment. Following the instructions in the manual provided with my course i keep getting this error message: "Error in plot.xy(xy, type, ...) : invalid plot type '1'" The commands i have entered are: >x=s

Re: [R] no output when run densityplot...

2008-08-26 Thread Ben Bolker
John Sanabria ece.uprm.edu> writes: > > Hi, > > I have downloaded a R script from > http://www.wessa.net/rwasp_edauni.wasp#output. > This script produces a densityplot graphic, amongst others, when is > executed from the web page. > However, when I run it in my machine the *densityplot* funct

Re: [R] RCurl: using netrc with curlPerform

2008-08-26 Thread Martin Morgan
Hi Valerie -- curlPerform is expecting the url to be an option that is named, i.e., > myopts <-curlOptions(netrc=1) > url <- "http://www.omegahat.org/RCurl/testPassword/index.html"; > cat(curlPerform(url=url, .opts=myopts)) Basic Password Test Basic Password Test This is a test page. If yo

Re: [R] lattice: plotting an arbitrary number of panels, defining arbitrary groups

2008-08-26 Thread Alex Karner
Thanks Deepayan, works like a charm. A followup question though--I'd like to produce the same data on four panels with the final two "zoomed in", i.e. plotted with shorter x and y axes. Since I can't access panel.number in the prepanel function, and since updating the plot with lists of the new x

[R] RCurl: using netrc with curlPerform

2008-08-26 Thread Valerie Obenchain
Hello, I am having trouble getting the curlPerform function to authenticate using the .netrc file. From the documentation I've read it certainly seems as though this function should be able to authenticate via the .netrc file. The example I am using here comes from the "R as a Web Client- the

Re: [R] switch() usage

2008-08-26 Thread Michael A. Gilchrist
Hi Dan, No, I hadn't thought of that and it WORKS! I was hoping there'd be such a simple solution. I have new respect for the power of {} w/in R. Many thanks! Mike - Department of Ecology & Evolutionary Biology 569 Dabney Hall University

Re: [R] switch() usage

2008-08-26 Thread Nordlund, Dan (DSHS/RDA)
> -Original Message- > From: [EMAIL PROTECTED] > [mailto:[EMAIL PROTECTED] On Behalf Of Michael A. > Gilchrist > Sent: Tuesday, August 26, 2008 6:03 PM > To: r-help@r-project.org > Subject: [R] switch() usage > > Hello, > > I am wondering if it is possible to run separate lines of > co

[R] switch() usage

2008-08-26 Thread Michael A. Gilchrist
Hello, I am wondering if it is possible to run separate lines of code within switch() as one can do in most languages. For example, I'd like to have switch execute a few lines of code based on the value passed to it. For example, index = 1 switch(index, command 1; command 2; comm

Re: [R] A Tip: lm, glm, and retained cases

2008-08-26 Thread Marc Schwartz
on 08/26/2008 07:31 PM (Ted Harding) wrote: > On 26-Aug-08 23:49:37, hadley wickham wrote: >> On Tue, Aug 26, 2008 at 6:45 PM, Ted Harding >> <[EMAIL PROTECTED]> wrote: >>> Hi Folks, >>> This tip is probably lurking somewhere already, but I've just >>> discovered it the hard way, so it is probably

Re: [R] Do I need a special package to run LSD tests?

2008-08-26 Thread Rolf Turner
On 27/08/2008, at 12:32 PM, michal33 wrote: Thanks for the answers, this one worked: library(Agricolae) No, it couldn't have. There is no such package as ``Agricolae''. There ***is*** a package called ``agricolae''. :-) cheers, Rolf Turner ###

Re: [R] Do I need a special package to run LSD tests?

2008-08-26 Thread michal33
Thanks for the answers, this one worked: >library(Agricolae) michal33 wrote: > > Hi there, > I am trying to run LSD.test(model) > > I used the following commands: > attach(model) > m1<- glm(ttl.m ~ site+year, family=quasipoisson, data= model) > df<-df.residual(m1) > MSerror<-deviance(m1)/df

Re: [R] A Tip: lm, glm, and retained cases

2008-08-26 Thread Ted Harding
On 26-Aug-08 23:49:37, hadley wickham wrote: > On Tue, Aug 26, 2008 at 6:45 PM, Ted Harding > <[EMAIL PROTECTED]> wrote: >> Hi Folks, >> This tip is probably lurking somewhere already, but I've just >> discovered it the hard way, so it is probably worth passing >> on for the benefit of those who mi

Re: [R] Problem with Integrate for NEF-HS distribution

2008-08-26 Thread Moshe Olshansky
If you look at your sech(pi*x/2) you can write it as sech(pi*x/2) = 2*exp(pi*x/2)/(1 + exp(pi*x)) For x < -15, exp(pi*x) < 10^-20, so for this interval you can replace sech(pi*x/2) by 2*exp(pi*x/2) and so the integral from -Inf to -15 (or even -10 - depends on your accuracy requirements) can be

Re: [R] A Tip: lm, glm, and retained cases

2008-08-26 Thread hadley wickham
On Tue, Aug 26, 2008 at 6:45 PM, Ted Harding <[EMAIL PROTECTED]> wrote: > Hi Folks, > This tip is probably lurking somewhere already, but I've just > discovered it the hard way, so it is probably worth passing > on for the benefit of those who might otherwise hack their > way along the same path. >

[R] A Tip: lm, glm, and retained cases

2008-08-26 Thread Ted Harding
Hi Folks, This tip is probably lurking somewhere already, but I've just discovered it the hard way, so it is probably worth passing on for the benefit of those who might otherwise hack their way along the same path. Say (for example) you want to do a logistic regression of a binary response Y on v

Re: [R] awkward behavior with densityplot function

2008-08-26 Thread Rolf Turner
See FAQ 7.22 On 27/08/2008, at 11:07 AM, John Sanabria wrote: Hi, I have the following script: t.R --- grafica <- function() { v <- read.csv('preprocessed/komolongma.ece.uprm.edu.active',sep=',') x <- as.ts(v$active) bitmap(file="output.png") densityplot(~x,col='blue',main='Densi

Re: [R] awkward behavior with densityplot function

2008-08-26 Thread Bill.Venables
Lattice functions do not create plots. In this respect they are quite different to functions like plot(...), hist(...) &c, which do create plots. If you want to see the plot from a lattice function, you need to print the object it creates. It's the action of printing that creates the graphical

[R] awkward behavior with densityplot function

2008-08-26 Thread John Sanabria
Hi, I have the following script: t.R --- grafica <- function() { v <- read.csv('preprocessed/komolongma.ece.uprm.edu.active',sep=',') x <- as.ts(v$active) bitmap(file="output.png") densityplot(~x,col='blue',main='Density Plot') dev.off() } grafica() t.R --- When I "sourced" i

Re: [R] loop with splitted data

2008-08-26 Thread Peter Dalgaard
jim holtman wrote: Is this what you want: y = c(rep(2,5),rep(3,5)) ma <- data.frame(x = 1:10, y=y ) splitted <- split(ma, ma$y) for (counter in (min(ma$y):max(ma$y))) + { + cat(counter, ":", splitted[[as.character(counter)]]$x, '\n') + } 2 : 1 2 3 4 5 3 : 6 7 8 9 10 But maybe thi

Re: [R] svymeans question

2008-08-26 Thread Doran, Harold
Indeed, missing data are the problem. The function removes any row with missing data and the means are based on the remaining rows. So, I wrote a function that just loops over each variable individually and organizes the data as I need it. -Original Message- From: James Reilly on behalf

Re: [R] lattice: plotting an arbitrary number of panels, defining arbitrary groups

2008-08-26 Thread Deepayan Sarkar
On Tue, Aug 26, 2008 at 2:26 PM, Alex Karner <[EMAIL PROTECTED]> wrote: > R Friends, > > I'm running R2.7.1 on Windows XP. > > I'm trying to get some lattice functionality which I have not seen > previously documented--I'd like to plot the exact same data in multiple > panels but changing the group

Re: [R] loop with splitted data

2008-08-26 Thread jim holtman
Is this what you want: > y = c(rep(2,5),rep(3,5)) > ma <- data.frame(x = 1:10, y=y ) > splitted <- split(ma, ma$y) > for (counter in (min(ma$y):max(ma$y))) + { + cat(counter, ":", splitted[[as.character(counter)]]$x, '\n') + } 2 : 1 2 3 4 5 3 : 6 7 8 9 10 On Tue, Aug 26, 2008 at 6:37 AM, Knut

Re: [R] lattice plotting character woes

2008-08-26 Thread Murray Jorgensen
[Rolf, this crosses with your reply. I will look at your email next.] I pasted the wrong code last time. The following code is supposed to illustrate my problem with lattice plotting character changes. patches <- structure(list(URBAN_AREA = structure(c(2L, 19L, 23L, 2L, 19L, 23L, 2L, 19L, 23

Re: [R] svymeans question

2008-08-26 Thread James Reilly
On 26/8/08 9:40 AM, Doran, Harold wrote: Computing the mean of the item by itself with svymeans agrees with the sample mean mean(lower_dat$W524787, na.rm=T) [1] 0.8555471 Compare this to the value in the row 9 up from the bottom to see it is different. You might be omitting more cases due

[R] lattice: plotting an arbitrary number of panels, defining arbitrary groups

2008-08-26 Thread Alex Karner
R Friends, I'm running R2.7.1 on Windows XP. I'm trying to get some lattice functionality which I have not seen previously documented--I'd like to plot the exact same data in multiple panels but changing the grouping variable each time so that each panel highlights a different feature of the data

Re: [R] stats tests on large tables

2008-08-26 Thread Rolf Turner
On 27/08/2008, at 3:52 AM, Richard Emes wrote: I have a large table of data which i can read in using read.table. I then want to conduct various tests on the data. Is there a simple way to conduct these tests by specifying the column headers which relate to different conditions of the experi

Re: [R] Latin squares in R

2008-08-26 Thread John Kane
Is this of any help http://cran.r-project.org/web/views/ExperimentalDesign.html --- On Tue, 8/26/08, Edna Bell <[EMAIL PROTECTED]> wrote: > From: Edna Bell <[EMAIL PROTECTED]> > Subject: [R] Latin squares in R > To: [EMAIL PROTECTED] > Received: Tuesday, August 26, 2008, 1:55 PM > Dear R Gurus:

[R] Potential Error/Bug?: addition of NULL during arithmetic

2008-08-26 Thread Eric DeWitt
I encountered an error that does not make sense to me given my reading of the documentation and does not appear to be referenced in the list archives or online. The error occurred when a function received a NULL value rather than a numeric value as a parameter and then attempted to use the NULL

Re: [R] R for Windows GUI closes when I try to read.spss

2008-08-26 Thread Roderick Harrison
Can't thank you enough! This worked! >>> "N'DOYE Souleymane" <[EMAIL PROTECTED]> 8/26/2008 1:20 AM >>> Hi Roderick, Let me suggest you to save your spss file in txt, and use the read.table or read.csv fonction. That is how I proceed. I hope it will help you, Best regards On Mon, Aug 25,

Re: [R] How many parameters does my model (gls) have?

2008-08-26 Thread roger koenker
?extractAIC url:www.econ.uiuc.edu/~rogerRoger Koenker email[EMAIL PROTECTED]Department of Economics vox: 217-333-4558University of Illinois fax: 217-244-6678Champaign, IL 61820 On Aug 26, 2008, at 2:27 PM, Mark Na wrote:

[R] How many parameters does my model (gls) have?

2008-08-26 Thread Mark Na
Hello, Is there a way to output the number of parameters in my model (gls)? I can count the number of estimates, but I'd like to use the number of parameters as an R object. Thanks, Mark __ R-help@r-project.org mailing list https://stat.ethz.ch/mai

Re: [R] Problem with Integrate for NEF-HS distribution

2008-08-26 Thread xia wang
Got it. Thanks so much! Xia From: [EMAIL PROTECTED] To: [EMAIL PROTECTED] CC: r-help@r-project.org Subject: RE: [R] Problem with Integrate for NEF-HS distribution Date: Tue, 26 Aug 2008 14:50:18 -0400 Try the following: sech<-function(X) 2/(exp(-X)+exp(X)) your.integrand <- functi

Re: [R] stats tests on large tables

2008-08-26 Thread John Kane
Try t.test(data1[,1],data1[,2]) for the first two columns of data1. --- On Tue, 8/26/08, Richard Emes <[EMAIL PROTECTED]> wrote: > From: Richard Emes <[EMAIL PROTECTED]> > Subject: [R] stats tests on large tables > To: r-help@r-project.org > Received: Tuesday, August 26, 2008, 11:52 AM > I ha

[R] error message in cor.dist

2008-08-26 Thread Tanya Yatsunenko
Hello, I am trying to calculate pairwise Pearson correlation distances, and using biodist package, function "cor.dist". I start with a table of 4 rows and about 10 columns. (each of 4 samples, or rows have values in each of the 10 categories, no zeros or NAs). I am getting an error message: >

Re: [R] Two envelopes problem

2008-08-26 Thread John C Frain
A very important point is missing here. If there is x in one envelope and 2x in the other the expected gain is 3x/2. If the idea is to switch after observing the second envelope the expected gain is again 3x/2. In the case being put x will be either 5 or 10. But x is a parameter and in this cas

Re: [R] Problem with Integrate for NEF-HS distribution

2008-08-26 Thread Ravi Varadhan
Try the following: sech<-function(X) 2/(exp(-X)+exp(X)) your.integrand <- function(X) {0.5*cos(theta)*exp(X*theta)*sech(pi*X/2)} my.integrand <- function(X) {0.5 * cos(theta) * 2 / (exp(-pi*X/2 - X*theta) + exp(pi*X/2 - X*theta)) } theta <- -1 my.integrand(-800) your.integrand(-800) Do y

Re: [R] sequence with start and stop positions

2008-08-26 Thread Ray Brownrigg
And somewhat faster still (YMMV): unlist(mapply(":", start, stop)) HTH, Ray Brownrigg Victoria University of Wellington Christos Hatzis wrote: Try: unlist(mapply(seq, c(1,20,50), c(7,25,53))) [1] 1 2 3 4 5 6 7 20 21 22 23 24 25 50 51 52 53 -Christos -Original Message- Fr

Re: [R] Problem with Integrate for NEF-HS distribution

2008-08-26 Thread xia wang
Thanks. I revised the code but it doesn't make difference. The cause of the error is just as stated in the ?integrate " If the function is approximately constant (in particular, zero) over nearly all its range it is possible that the result and error estimate may be seriously wrong. " I hav

[R] stats tests on large tables

2008-08-26 Thread Richard Emes
I have a large table of data which i can read in using read.table. I then want to conduct various tests on the data. Is there a simple way to conduct these tests by specifying the column headers which relate to different conditions of the experiment? e.g. data1 <- read.table("test.table", heade

Re: [R] Two envelopes problem

2008-08-26 Thread markleeds
beautiful. now, i think i got it. the fact that the calculation works in the additive case doesn't make the calculation correct. the expected value calculation is kind of assuming that the person putting the things in the envelopes chooses what's in the second envelope AFTER knowing what's

Re: [R] Dramatic slowdown of R 2.7.2?

2008-08-26 Thread Peter Dalgaard
Marek Wielgosz wrote: Dear R users/developers, simple comparison of code execution time of R 2.7.1 and R 2.7.2 shows a dramatic slowdown of the newer version. Rprof() identifies .Call function as a main cause (see the code below). What happened with R 2.7.2? I don't see much of a difference,

Re: [R] plot3d origin

2008-08-26 Thread Duncan Murdoch
On 8/26/2008 1:05 PM, Chibisi Chima-Okereke wrote: Hi all, I am trying to do a 3d plot where the x,y,z axes intersects with the origin (0,0,0) using the plot3d() funtion in the rgl package without success. I looked back at the past archives on this subject and someone suggested using djmrgl pack

Re: [R] Two envelopes problem

2008-08-26 Thread Duncan Murdoch
On 8/26/2008 1:12 PM, [EMAIL PROTECTED] wrote: Duncan: Just one more thing which Heinz alerted me to. Suppose that we changed the game so that instead of being double or half of X, we said that one envelope will contain X + 5 and the other contains X-5. So someone opens it and sees 10 dollars.

[R] Latin squares in R

2008-08-26 Thread Edna Bell
Dear R Gurus: What would be the best way to evaluate a Latin square problem, please? Does it work in Rcmdr, please? thanks, Edna Bell __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide ht

Re: [R] Maintaining repeated ID numbers when transposing with reshape

2008-08-26 Thread jcarmichael
Thank you for your suggestion, I will play around with it. I guess my concern is that I need each test result to occupy its own "cell" rather than have one or more in the same row. Adaikalavan Ramasamy-2 wrote: > > There might be a more elegant way of doing this but here is a way of > doing it

Re: [R] Two envelopes problem

2008-08-26 Thread S Ellison
>>> Duncan Murdoch <[EMAIL PROTECTED]> 26/08/2008 16:17:34 >>> >>If this is indeed the case, switch; the expected gain is >>positive because _you already have the information that you hold the >> median value of the three possibilities_. The tendency when presented > >with the problem is to reaso

Re: [R] Two envelopes problem

2008-08-26 Thread Farley, Robert
So if I put $10 and $20 into the envelopes, then told you that the values were multiples of $10, it would be wrong for you to assess probabilities on $100, $1,000,000 and so on? :-) But what if you reasoned that there were far more multiples of 10 above 20 than below 20? What if I was really ev

Re: [R] Two envelopes problem

2008-08-26 Thread markleeds
Duncan: Just one more thing which Heinz alerted me to. Suppose that we changed the game so that instead of being double or half of X, we said that one envelope will contain X + 5 and the other contains X-5. So someone opens it and sees 10 dollars. Now, their remaining choices are 5 and 15 so the

Re: [R] sequence with start and stop positions

2008-08-26 Thread Charles C. Berry
On Tue, 26 Aug 2008, Chris Oldmeadow wrote: Hi, I have a vector of start positions, and another vector of stop positions, eg start<-c(1,20,50) stop<-c(7,25,53) Is there a quick way to create a sequence from these vectors? new<-c(1,2,3,4,5,6,7,20,21,22,23,24,25,50,51,52,53) Vectorize t

[R] plot3d origin

2008-08-26 Thread Chibisi Chima-Okereke
Hi all, I am trying to do a 3d plot where the x,y,z axes intersects with the origin (0,0,0) using the plot3d() funtion in the rgl package without success. I looked back at the past archives on this subject and someone suggested using djmrgl package. I searched and found it, installed it but when I

Re: [R] Problem with Integrate for NEF-HS distribution

2008-08-26 Thread xia wang
Thanks so much. It works well in my MCMC sampling. May I know why re-writing the integrand can solve the problem? I have been thinking it was the skewness of the distribution brought the error. Thanks! Xia > From: [EMAIL PROTECTED] > To: [EMAIL PROTECTED]; r-help@r-project.org > Subject:

[R] no output when run densityplot...

2008-08-26 Thread John Sanabria
Hi, I have downloaded a R script from http://www.wessa.net/rwasp_edauni.wasp#output. This script produces a densityplot graphic, amongst others, when is executed from the web page. However, when I run it in my machine the *densityplot* function produces any output, I mean a blank graphic. But,

[R] Dramatic slowdown of R 2.7.2?

2008-08-26 Thread Marek Wielgosz
Dear R users/developers, simple comparison of code execution time of R 2.7.1 and R 2.7.2 shows a dramatic slowdown of the newer version. Rprof() identifies .Call function as a main cause (see the code below). What happened with R 2.7.2? Kind regards Marek Wielgosz Bayes Consulting ###

[R] package install failure

2008-08-26 Thread George Georgalis
Hello, the arm package is failing to install, it says I need gnu make but it's not clear how I specify which make to use in the R environment. For example I already have gmake installed. How to I instruct R to use it? * Installing *source* package 'Matrix' ... usage: make [-BeikNnqrstWX] [-D vari

[R] R binaries for linux on G4 Powerpc?

2008-08-26 Thread Tariq Perwez
Hi Everyone I just installed Yellow Dog Linux (v 5.02) on an old G4 Powerpc replacing the Mac OSX. The system is running beautifully. I would like to install R on this system. I am not sure how to go about doing it. I have installed R on my Ubuntu system as well as on Mac OSX but there are binarie

Re: [R] Problem with Integrate for NEF-HS distribution

2008-08-26 Thread Ravi Varadhan
Hi, Simply re-write your integrand as follows: integrand <- function(X) {0.5 * cos(theta) * 2 / (exp(-pi*X/2 - X*theta) + exp(pi*X/2 - X*theta)) } Now the problem goes away. > theta <- -1 > integrate(integrand, -Inf, 1) 0.9842315 with absolute error < 1.2e-05 This would work for all theta su

Re: [R] permutation cycles

2008-08-26 Thread Martin Maechler
I'm replying in public to this, since it relates to an R-help thread of April 15-16, 2008 (and am also adding back 'References:' to one of those postings of mine). > Mark Segal < mark at biostat ucsf > > on Mon, 25 Aug 2008 11:25:05 -0700 writes: > Hi Martin, > You posted the

Re: [R] embedded examples

2008-08-26 Thread hadley wickham
You might also want to look at existing visualisation applications that connect with R: * http://ggobi.org * http://rosuda.org/mondrian * http://rosuda.org/software/Gauguin/gauguin.html to name a few. Hadley On Tue, Aug 26, 2008 at 10:31 AM, EBo <[EMAIL PROTECTED]> wrote: > > I am working on

Re: [R] Two envelopes problem

2008-08-26 Thread Mark Leeds
Hi Duncan: I think I get you. Once one takes expectations, there is an underlying assumption about the distribution of X and , in this problem, we don't have one so taking expectations has no meaning. If the log utility "fixing" the problem is purely just a coincidence, then it's surely an odd one

Re: [R] environments

2008-08-26 Thread Duncan Murdoch
On 8/26/2008 9:44 AM, Peter Dalgaard wrote: Antje wrote: Okay, I see, there is no really "easy" way (I was wondering whether I can set an environment as default for new created variables). Is there any difference if I call myenv$myvar <- 10 or assign("myvar",10, env=myenv) ? No. And with(myen

[R] embedded examples

2008-08-26 Thread EBo
I am working on embedding R into some visualization research programs. Can any point me to a collection of embedded and standalone R/C/C++ examples? The documentation is to terse for me to figure out how to develop this and I am looking for some simple examples to study. Thanks and best regar

Re: [R] Two envelopes problem

2008-08-26 Thread Duncan Murdoch
On 8/26/2008 9:51 AM, Mark Leeds wrote: Duncan: I think I see what you're saying but the strange thing is that if you use the utility function log(x) rather than x, then the expected values are equal. I think that's more or less a coincidence. If I tell you that the two envelopes contain X

[R] more dot plots on 1 page

2008-08-26 Thread Van den Berge Joke
Hi, I would like to have six dot plots on one page. I make the plots in a 'for loop' because it is six times the same graph but for different subjects (species). I tried it with "par(mfrow=c(3,2), oma=c(3,3,2,0), mar=c(2,2,2,2))"; but this does not work for dot plots apparently. Then I tried

Re: [R] Two envelopes problem

2008-08-26 Thread Heinz Tuechler
Mark My experience was similarly frustrating. Maybe formulating the problem a bit differently could help to clarify it. State it like this: Someone chooses an amount of money x. He puts 2x/3 of it in one envelope and x/3 in an other. There is no assumption about the distribution of x. If you

Re: [R] SQL Primer for R

2008-08-26 Thread Thomas Lumley
On Tue, 26 Aug 2008, ivo welch wrote: Sorry, chaps. I need one more: dbDisconnect(con.in) Error in sqliteCloseConnection(conn, ...) : RS-DBI driver: (close the pending result sets before closing this connection) I am pretty sure I have fetched everything there is to be fetched. dbClea

Re: [R] How to do a meta-analysis plot

2008-08-26 Thread Thomas Lumley
On Mon, 25 Aug 2008, Jorge Ivan Velez wrote: My problem is that I don't have the raw data as rmeta _requires_ and, even when I have my data set in the _same_ (?) format that summary(a), when I tried plot(mydata) it doesn't work. No, it doesn't _require_ that. If you just want a forest plot the

Re: [R] processing subset lists and then plot(density())

2008-08-26 Thread stephen sefick
definitly need to look into ggplot- very cool. thanks On Tue, Aug 26, 2008 at 10:20 AM, ONKELINX, Thierry <[EMAIL PROTECTED]> wrote: > > Here's a solution with ggplot2 > > library(ggplot2) > ggplot(na.omit(d), aes(x = EPT.Taxa, colour = Site)) + geom_density() > ggplot(na.omit(d), aes(x = EPT.Taxa

Re: [R] savePlot() does not save plot with format set

2008-08-26 Thread Monica Pisica
Did you try: savePlot("test.bmp", type = "bmp") Monica Message: 118 Date: Tue, 26 Aug 2008 10:29:13 +0100 From: "Luis Ridao Cruz" Subject: [R] savePlot() does not save plot with format set To: Message-ID: Content-Type: t

Re: [R] Two envelopes problem

2008-08-26 Thread Mark Difford
... To pick up on what Mark has said: it strikes me that this is related to the simplex, where the bounded nature of the vector space means that normal arithmetical operations (i.e. Euclidean) don't work---that is, they can be used, but the results are wrong. Covariances and correlations for inst

Re: [R] processing subset lists and then plot(density())

2008-08-26 Thread ONKELINX, Thierry
Here's a solution with ggplot2 library(ggplot2) ggplot(na.omit(d), aes(x = EPT.Taxa, colour = Site)) + geom_density() ggplot(na.omit(d), aes(x = EPT.Taxa)) + geom_density() + facet_grid(Site ~ .) HTH, Thierry ir. Th

Re: [R] String search: Return "closest" match

2008-08-26 Thread Werner Wernersen
That works perfectly, great. Thanks a lot for that Richard! Werner - Ursprüngliche Mail Von: "[EMAIL PROTECTED]" <[EMAIL PROTECTED]> An: Werner Wernersen <[EMAIL PROTECTED]> CC: [EMAIL PROTECTED]; [EMAIL PROTECTED] Gesendet: Dienstag, den 26. August 2008, 14:10:11 Uhr Betreff: Re: [R

Re: [R] Two envelopes problem

2008-08-26 Thread Mark Leeds
Duncan: I think I see what you're saying but the strange thing is that if you use the utility function log(x) rather than x, then the expected values are equal. Somehow, if you are correct and I think you are, then taking the log , "fixes" the distribution of x which is kind of odd to me. I'm sorry

[R] processing subset lists and then plot(density())

2008-08-26 Thread stephen sefick
d <- structure(list(Site = structure(c(8L, 12L, 7L, 6L, 11L, 5L, 10L, 4L, 3L, 2L, 1L, 9L, 8L, 12L, 7L, 6L, 11L, 5L, 10L, 4L, 3L, 2L, 1L, 9L, 8L, 12L, 7L, 6L, 11L, 5L, 10L, 4L, 3L, 2L, 1L, 9L, 8L, 12L, 7L, 6L, 11L, 5L, 10L, 4L, 3L, 2L, 1L, 9L, 8L, 12L, 7L, 6L, 11L, 5L, 10L, 4L, 3L, 2L, 1L, 9L, 8L, 1

Re: [R] options("contrasts")

2008-08-26 Thread Ted Harding
On 26-Aug-08 10:30:30, David Epstein wrote: > Code: >> options("contrasts") > $contrasts >factor ordered > "contr.treatment" "contr.poly" > > I want to change the first entry ONLY, without retyping "contr.poly". > How do I do it? I have tried various possibilities and c

Re: [R] environments

2008-08-26 Thread Peter Dalgaard
Antje wrote: > Okay, I see, there is no really "easy" way (I was wondering whether I > can set an environment as default for new created variables). Is there > any difference if I call > > myenv$myvar <- 10 > or > assign("myvar",10, env=myenv) > ? > No. And with(myenv, myvar <- 10) is also the same

[R] svymeans question

2008-08-26 Thread Doran, Harold
I have the following code which produces the output below it clus1 <- svydesign(ids = ~schid, data = lower_dat) items <- as.formula(paste(" ~ ", paste(lset, collapse= "+"))) rr1 <- svymean(items, clus1, deff='replace', na.rm=TRUE) > rr1 mean SE DEff W525209 0.719748 0.015606

Re: [R] environments

2008-08-26 Thread Antje
Okay, I see, there is no really "easy" way (I was wondering whether I can set an environment as default for new created variables). Is there any difference if I call myenv$myvar <- 10 or assign("myvar",10, env=myenv) ? Antje Douglas Bates schrieb: On Tue, Aug 26, 2008 at 6:07 AM, Henrique D

Re: [R] environments

2008-08-26 Thread Peter Dalgaard
Douglas Bates wrote: > As Henrique said, the canonical way of assigning a value within an > environment is the "assign". A more obscure, but also more effective, > approach is evalq which quotes an expression then evaluates it in the > given environment. For example > > >> env <- new.env() >>

Re: [R] String search: Return "closest" match

2008-08-26 Thread Richard . Cotton
> I have to match names where names can be recorded with errors or additions. > Now I am searching for a string search function which returns always > the "closest" match. E.g. searching for "Washington" it should > return only Washington but not Washington, D.C. But it also could be > that the

Re: [R] environments

2008-08-26 Thread Douglas Bates
On Tue, Aug 26, 2008 at 6:07 AM, Henrique Dallazuanna <[EMAIL PROTECTED]> wrote: > I think you need assign, see ?assign for more details. > On Tue, Aug 26, 2008 at 6:02 AM, Antje <[EMAIL PROTECTED]> wrote: >> Hi there, >> I try to understand the usage of environments but I'm not sure if I get it.

Re: [R] SQL Primer for R

2008-08-26 Thread ivo welch
Sorry, chaps. I need one more: > dbDisconnect(con.in) Error in sqliteCloseConnection(conn, ...) : RS-DBI driver: (close the pending result sets before closing this connection) > I am pretty sure I have fetched everything there is to be fetched. I am not sure what I need to do to say goodbye (

Re: [R] Using interactive plots to get information about data points

2008-08-26 Thread Michael Bibo
jcarmichael gmail.com> writes: > > > Thank you for the GGobi reference, it is a very handy tool! My main goal, > however, is to be able to identify univariate outliers (with boxplots for > example), and I'm having a hard time getting the rggobi package to do that. > Hmmm... I guess because G

Re: [R] savePlot() does not save plot with format set

2008-08-26 Thread S Ellison
Strictly, you need to type the extension _if your filename or path include a period (".")_ but not otherwise. The filename "test" alone will be saved as paste("test",type). So will, for example, "/plots/test". But filenames such as "test.it" or "../plots/test" will not include the extension automa

Re: [R] Two envelopes problem

2008-08-26 Thread Duncan Murdoch
On 26/08/2008 7:54 AM, Jim Lemon wrote: Hi again, Oops, I meant the expected value of the swap is: 5*0.5 + 20*0.5 = 12.5 Too late, must get to bed. But that is still wrong. You want a conditional expectation, conditional on the observed value (10 in this case). The answer depends on the d

Re: [R] How to do a meta-analysis plot

2008-08-26 Thread Jonathan Baron
Another way to do it (based on summary data): http://finzi.psych.upenn.edu/R/Rhelp02a/archive/131342.html -- Jonathan Baron, Professor of Psychology, University of Pennsylvania Home page: http://www.sas.upenn.edu/~baron __ R-help@r-project.org mailing

Re: [R] Two envelopes problem

2008-08-26 Thread Jim Lemon
Hi again, Oops, I meant the expected value of the swap is: 5*0.5 + 20*0.5 = 12.5 Too late, must get to bed. Jim __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org

[R] String search: Return "closest" match

2008-08-26 Thread Werner Wernersen
Hi, I have to match names where names can be recorded with errors or additions. Now I am searching for a string search function which returns always the "closest" match. E.g. searching for "Washington" it should return only Washington but not Washington, D.C. But it also could be that the list

Re: [R] Two envelopes problem

2008-08-26 Thread Jim Lemon
Hi Mario, If I understand your problem statement, the random choice of one of the two envelopes ensures that the probability of choosing one or the other is 0.5. If you find 10 (units, I can't find the pound symbol on this keyboard), there is an equal likelihood that the other envelope contains 5 o

Re: [R] How to do a meta-analysis plot

2008-08-26 Thread Michael Dewey
At 19:44 25/08/2008, Jorge Ivan Velez wrote: Dear R-list, I'd like to do a meta-analysis plot similar to Since these plots are known as forest plots ?forestplot might help you. As it says you have to do a bit more work but you do get much more flexibility install.packages('rmeta') require(r

Re: [R] options("contrasts")

2008-08-26 Thread Duncan Murdoch
On 26/08/2008 6:30 AM, David Epstein wrote: Code: options("contrasts") $contrasts factor ordered "contr.treatment" "contr.poly" I want to change the first entry ONLY, without retyping "contr.poly". How do I do it? I have tried various possibilities and cannot get an

Re: [R] savePlot() does not save plot with format set

2008-08-26 Thread Henrique Dallazuanna
You need type the extension of the file: plot(rnorm(10)) savePlot("test.png", type="png") savePlot("test.bmp", type="bmp") On Tue, Aug 26, 2008 at 6:29 AM, Luis Ridao Cruz <[EMAIL PROTECTED]> wrote: > R-help, > > Whenever I try to save a plot with "savePlot" > the file is not stored in my hard d

Re: [R] environments

2008-08-26 Thread Henrique Dallazuanna
I think you need assign, see ?assign for more details. On Tue, Aug 26, 2008 at 6:02 AM, Antje <[EMAIL PROTECTED]> wrote: > Hi there, > > I try to understand the usage of environments but I'm not sure if I get it. > I wrote a test script like this: > > testenv <- new.env(environment()) > > myfun <-

Re: [R] paste: multiple collapse arguments?

2008-08-26 Thread Henrique Dallazuanna
Try this also: paste(apply(matrix(x, 2), 2, paste, collapse = ' '), collapse = "\n") On Mon, Aug 25, 2008 at 8:36 PM, remko duursma <[EMAIL PROTECTED]> wrote: > > Dear R-helpers, > > I have a numeric vector, like: > > x <- c(1,2,3,4,5,6) > > I make this into a string for output to a text file, se

[R] loop with splitted data

2008-08-26 Thread Knut Krueger
Hi to all, seems to be simple, but I do not find the solution: What must I write for the splitted to get splitted$"3"$x and splitted$"3"$x y = c(rep(2,5),rep(3,5)) ma <- data.frame(x = 1:10, y=y ) splitted <- split(ma, ma$y) for (counter in (min(ma$y):max(ma$y))) { splitted$x } Rega

Re: [R] Variance-covariance matrix

2008-08-26 Thread Laura Bonnett
The standard treatment is the same in both comparison. How do you do a three-level treatment factor? I thought you had to have a censoring indicator which took values 0 or 1 not 1, 2 or 3? Thanks, Laura On Tue, Aug 26, 2008 at 11:05 AM, Peter Dalgaard <[EMAIL PROTECTED]>wrote: > Laura Bonnett

  1   2   >