[R] Re : BOOTSTRAP_CROSS VALIDATION

See the boot package  Justin BEM BP 1917 Yaoundé Tél (237) 99597295 (237) 22040246 De : per243 À : r-help@r-project.org Envoyé le : Lundi, 16 Mars 2009, 0h12mn 03s Objet : [R] BOOTSTRAP_CROSS VALIDATION I need a script that works for Bootstrap validation. C

[R] Fw: Fitting GUMBEL Distribution - CDF function and P P Plot

Dera R Helpers, I am re-posting my query. Please guide me. Maithili --- On Fri, 3/13/09, Maithili Shiva wrote: I am trying to fit the Gumbel distribution to a data. I am using lmom package. I am getting problem in Cumulative Distribution Function of Gumbel distribution as I am getting i

Re: [R] Testing for Inequality à la "select case"

> That's what I meant by element-by -element. A vector in R corresponds > to a row or a column in Excel, and a vector operation in R corresponds > to a row or column of formulae, e.g. > > Excel > A B C > 1) 5 10 a1+b1 (= 15) > 2) 3 2 a2+b2 (= 5) > etc. >

Re: [R] Problem with figure size when embedding fonts

Paul Johnson wrote: On Sat, Mar 14, 2009 at 1:51 PM, Frank E Harrell Jr wrote: Dear Colleagues: I need to make a graphic that uses the Nimbus rather than Helvetica font family so that the font can be embedded in the encapsulated postscript file. This is to satisfy a requirement from a journal

[R] transfer function in R

I want to forecast a time series Y using a model that includes previous values of Y and an exogenous time series X using a transfer function. The standard procedure as described in Box and Jenkins and numerous other references is to first fit an ARIMA model to X. Use the ARIMA model to computer res

Re: [R] primitives again

On Sun, 15 Mar 2009 14:23:40 +0100 Wacek Kusnierczyk wrote: > Edna Bell wrote: > > How do I find the functions which are primitives, please? > > > > you can scan the whole search path for functions that are primitives: > > primitives = sapply(search(), function(path) > with(as.envir

[R] BOOTSTRAP_CROSS VALIDATION

I need a script that works for Bootstrap validation. Could someone explain me when should I use the Bootstrap technical or Jackknife? Thanks -- View this message in context: http://www.nabble.com/BOOTSTRAP_CROSS-VALIDATION-tp22529500p22529500.html Sent from the R help mailing list archive at

Re: [R] Testing for Inequality à la "select case "

Using cut/split seems like gross overkill here. Among other things, you don't need to generate labels for all the different ranges. which(x<=range)[1] seems straightforward enough to me, but you could also use the built-in function findInterval. -s

Re: [R] Testing for Inequality à la "select case "

On Sun, Mar 15, 2009 at 6:34 PM, diegol wrote: >> If you'd do it element-by-element in Excel, why not do it >> element-by-element in R? > > Well, actually I was hoping for a vectorized solution so as to avoid > looping. That's what I meant by element-by -element. A vector in R corresponds to a ro

Re: [R] Problem with figure size when embedding fonts

On Sat, Mar 14, 2009 at 1:51 PM, Frank E Harrell Jr wrote: > Dear Colleagues: > > I need to make a graphic that uses the Nimbus rather than Helvetica font > family so that the font can be embedded in the encapsulated postscript file. >  This is to satisfy a requirement from a journal for electroni

Re: [R] Testing for Inequality à la "select case"

Hello Baptiste, Thanks so much for your help. This function which is basically your input wrapped with curly brackets seems to work alright: mr_2 <- function(x){ range= c(20,100,250,700,1000,Inf)*1000 perc = c(65,40,30,25,20,0)/100 min = c(0,14,40,75,175,250)*1000

Re: [R] dispcrepancy between aov F test and tukey contrasts results with mixed effects model

lba...@montana.edu wrote: Thanks Peter for the advice and quick response. I just want to clarify what you suggest. I should average values within a site then do a one-way anova to test for differnces between sites based on the 2 to 3 new samples per stand type -- and not use random effects for

Re: [R] Testing for Inequality à la "select case "

Hi, I don't use ?cut and ?split very much either, so this may not be good advice. From what I understood of your problem, I would try something along those lines, range= c(20,100,250,700,1000,Inf)*1000 perc = c(65,40,30,25,20,0)/100 min = c(0,14,40,75,175,250)*1000 range = c(0, range) x

Re: [R] Testing for Inequality à la "select case"

Hello Baptiste, I am not very sure how I'd go about that. Taking the range, perc and min vectors from Stavros' response: range= c(20,100,250,700,1000,Inf)*1000 perc = c(65,40,30,25,20,0)/100 min = c(0,14,40,75,175,250)*1000 For range to work as the breaks argument to "cut", I think

Re: [R] Testing for Inequality à la "select case"

Hello Stavros, > If you'd do it element-by-element in Excel, why not do it > element-by-element in R? Well, actually I was hoping for a vectorized solution so as to avoid looping. I need to use this formula on rather lengthy vectors and I wanted to put R's efficiency to some good use. In any cas

Re: [R] Tukey, planned contrasts or t-test without ANOV A? What is correct?

J S hotmail.com> writes: > I compare mean monthly body temperature between two age classes of turtles overwintering underground. > > lm(body_tem ~ Month*Year*Age_Class) > TukeyHSD(aov(body_tem ~ Month*Year*Age_Class, a)) > > The Tukey HSD as well as the planned contrasts method showed signific

Re: [R] Testing for Inequality à la "select case "

On Sun, Mar 15, 2009 at 4:12 PM, diegol wrote: > ...This could be done in Excel much tidier in my opinion (especially the > range_aux part), element by element (cell by cell)... If you'd do it element-by-element in Excel, why not do it element-by-element in R? Create a table with the limits of t

Re: [R] Testing for Inequality à la "select case "

Hi, I think you could get a cleaner solution using ?cut to split your data in given ranges (the break argument), and then using this factor to give the appropriate percentage. Hope this helps, baptiste On 15 Mar 2009, at 20:12, diegol wrote: Using R 2.7.0 under WinXP. I need to write

[R] Testing for Inequality à la "select case"

Using R 2.7.0 under WinXP. I need to write a function that takes a non-negative vector and returns the parallell maximum between a percentage of this argument and a fixed value. Both the percentages and the fixed values depend on which interval x falls in. Intervals are as follows: >From |

[R] mvpart error - is.leaf

Hello, When trying to run mvpart either specifying my own parameters or using the defaults, I get the following error: Error in all(is.leaf) : unused argument(s) (c(FALSE, TRUE, FALSE, FALSE, TRUE, TRUE, TRUE)) As far as I can tell, is.leaf is part of the dendrogam package, so I'm assuming the

Re: [R] SEM model testing with identical goodness of fits (2)

The purpose of carrying this CFA is to test the validity of a new developed scale "tr" with "v*" items, other two scales "weber" and "tp" are existing scales that measures specific risk attitudes. I am not sure if a simple correlation analysis is adequate to this purpose or not, thus the CFA

Re: [R] Contour plots of four two-dimensional matrices

You would use layout to set up the page in base graphics. It sets up the page to receive multiple plots. Unfortunately, this will *not* give you side by side plots because filled.contour is restricted to a full page per its help page layout(matrix(c(1,2,3,4), 2,2 byrow=TRUE) for (i in 1:4)

[R] Axes crossing at origin

Hi, I'm having a bit of trouble with the axes in my plots. I don't like the way R does not have them cross in the origin. Is there another plot/axis function? i tried using abline as suggested by someone from this list, but in my case this gives no satisfactory result, as the abline does sometimes

Re: [R] Contour plots of four two-dimensional matrices

I want to plot them side by side. On Sun, Mar 15, 2009 at 12:41 PM, David Winsemius wrote: > What is it that you want to do with these 4 plots? Overlay them with > different color contours or plot them side-by-side on the same page? > > ?par # for filled.contour but the implementation will be di

[R] Yet another large file question.

I am using the XML package to form a rather large XML file. It seems to go OK untill the file length gets larger than about 30Mb then it seems that the last tokens of the xml file are unmatched. It is almost like the file hasn't been flushed because the file is OK with the exception of the last

Re: [R] SEM model testing with identical goodness of fits (2)

Thanks for the clear clarification. The suggested bi-factor solution sounds attractive. I am going to check it in details. regards, William Revelle wrote: Dear Hyena, Your model is of three correlated factors accounting for the observed variables. Those three correlations may be accounted

Re: [R] dispcrepancy between aov F test and tukey contrasts results with mixed effects model

Thanks Peter for the advice and quick response. I just want to clarify what you suggest. I should average values within a site then do a one-way anova to test for differnces between sites based on the 2 to 3 new samples per stand type -- and not use random effects for site? Or, because I've redu

Re: [R] xyplot of a specific ID number

Using built in data frame CO2 try this where Type is a 2 level factor. library(lattice) xyplot(uptake ~ conc | Type, CO2) xyplot(uptake ~ conc | Type, CO2)[1] xyplot(uptake ~ conc | Type, CO2)[2] On Sun, Mar 15, 2009 at 12:35 PM, Sachi Ito wrote: > Dear R list members, > I have a question regard

Re: [R] SEM model testing with identical goodness of fits (2)

Dear Hyena, OK -- I see that what you're trying to do is simply to fit a confirmatory factor-analysis model. The two models that you're considering aren't really different -- they are, as I said, observationally equivalent, and fit the data poorly. You can *assume* a common higher-level factor a

Re: [R] xyplot of a specific ID number

Would have help if you had offered complete output for your efforts at using subset. This should work (on the assumption that ID is of type numeric): xyplot(PA ~ CRPC + CRPT , data = subset(redinteract, ID == 301) ) On Mar 15, 2009, at 12:35 PM, Sachi Ito wrote: Dear R list members, I h

Re: [R] Contour plots of four two-dimensional matrices

What is it that you want to do with these 4 plots? Overlay them with different color contours or plot them side-by-side on the same page? ?par # for filled.contour but the implementation will be different for those two options. contourplot is is a lattice plotting function. See Figure 6.1

[R] xyplot of a specific ID number

Dear R list members, I have a question regarding xyplot. I managed to make a xyplot of all the IDs by using the syntax below: xyplot(PA ~ CRPC + CRPT | ID, data = redinteract) Now, I'd like to make a graph of a specific ID number (e.g., only ID number 301). I thought I could use "subset", but i

[R] Contour plots of four two-dimensional matrices

I have four large two-dimensional matrices of which I want to create contour plots. Something like filled.contour() contourplot() works but only gives me one plot at a time. If I combine the four matrices into one three-dimensional matrix, which I'll name "seven", there should be a way of doing s

Re: [R] SEM model testing with identical goodness of fits (2)

Dear Hyena, Your model is of three correlated factors accounting for the observed variables. Those three correlations may be accounted for equally well by correlations (loadings) of the lower order factors with a general factor. Those two models are indeed equivalent models and will, as a c

Re: [R] SEM model testing with identical goodness of fits (2)

Dear John, Thanks for the reply. Maybe I had used wrong terminology, as you pointed out, in fact, variables "prob*", "o*" and "v*" are indicators of three latent variables(scales): weber, tp, and tr respectively. So variables "prob*", "o*" and "v*" are exogenous variables. e.g., variable

Re: [R] persp plot + plotting grid lines

On 15/03/2009 10:07 AM, Kingsford Jones wrote: Building on Duncan's code, here's an approximation to the Matlab 'peaks' plot referred to by Pedro: peaks <- function(x, y) { 3 * (1-x)^2 * exp(-(x^2)-(y+1)^2) - 10 * (x/5-x^3-y^5) * exp(-x^2-y^2) - 1/3*exp(-(x+1)^2-y^2)} x <- y <- seq(-3,3,.1)

Re: [R] primitives again

Thank you On Sun, Mar 15, 2009 at 8:23 AM, Wacek Kusnierczyk wrote: > Edna Bell wrote: >> How do I find the functions which are primitives, please? >> > > you can scan the whole search path for functions that are primitives: > >    primitives = sapply(search(), function(path) >       with(as.envi

Re: [R] builtin vs. closure

Thank you On Sun, Mar 15, 2009 at 8:36 AM, Duncan Murdoch wrote: > On 15/03/2009 12:00 AM, Edna Bell wrote: >> >> Dear R Gurus: >> >> I'm working slowly through "R Programming for Bioinformatics", which >> is really interesting! >> >> Anyway, my question now is:  what determines if a function is

Re: [R] Help plase with simple loop

I don't think you have gotten the basic idea of functions in R. Those functions would return only the value of the last evaluated expression, e.g. (1+par[1]) in the case of f1, but most of the code appears to have no effect. See this simple example: > x1 <- 4 > f1 <- function(x) x1 <- x > f

Re: [R] What is the best package for large data cleaning (not statistical analysis)?

Hi Sean, you should think about storing the data externally in a sql database. this makes you very flexible and you can do a lot of manipultaion directly in the db. with the help of stored procedures for example in a postgreSQL db you can use almost any preferred languege to manipulate th

Re: [R] persp plot + plotting grid lines

Building on Duncan's code, here's an approximation to the Matlab 'peaks' plot referred to by Pedro: peaks <- function(x, y) { 3 * (1-x)^2 * exp(-(x^2)-(y+1)^2) - 10 * (x/5-x^3-y^5) * exp(-x^2-y^2) - 1/3*exp(-(x+1)^2-y^2)} x <- y <- seq(-3,3,.1) z <- outer(x,y, peaks) z2 <- 10 * round(c(z) + ab

[R] Help plase with simple loop

Dear All, I’m a new R user. How can I write code below more efficiently (using a loop for example)? f1 <-function(par){x1 <- par[1]; x2 <- par[2];x3 <- par[3] ; x4 <- par[4] ; (1+x1)} f2 <-function(par){x1 <- par[1]; x2 <- par[2];x3 <- par[3] ; x4 <- par[4] ;(1+x2)} f3 <-function(par){x1 <- p

Re: [R] builtin vs. closure

On 15/03/2009 12:00 AM, Edna Bell wrote: Dear R Gurus: I'm working slowly through "R Programming for Bioinformatics", which is really interesting! Anyway, my question now is: what determines if a function is a builtin vs. a closure, please? Closure is the normal type of function written in R

Re: [R] primitives again

Edna Bell wrote: > How do I find the functions which are primitives, please? > you can scan the whole search path for functions that are primitives: primitives = sapply(search(), function(path) with(as.environment(path), Filter(is.primitive, lapply(ls(), get primitives is a lis

Re: [R] [OT] two question about color space.

I've put together a rough R port of that C code [*] in a package on r- forge: http://r-forge.r-project.org/plugins/scmsvn/viewcvs.php/pkg/spectral/?root=photonics http://r-forge.r-project.org/R/?group_id=160 ( package spectral, will be built overnight ) There is a lot of optimization and

Re: [R] SEM model testing with identical goodness of fits (2)

Dear hyena, > -Original Message- > From: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org] On > Behalf Of hyena > Sent: March-15-09 4:25 AM > To: r-h...@stat.math.ethz.ch > Subject: Re: [R] SEM model testing with identical goodness of fits (2) > > Dear John, > > Than

[R] Tukey, planned contrasts or t-test without ANOVA? What is correct?

Dear R community, I compare mean monthly body temperature between two age classes of turtles overwintering underground. lm(body_tem ~ Month*Year*Age_Class) TukeyHSD(aov(body_tem ~ Month*Year*Age_Class, a)) The Tukey HSD as well as the planned contrasts method showed significant difference

Re: [R] What is the best package for large data cleaning (not statistical analysis)?

Dear Jim: Thanks for your reply. Looks to me, you were using batching. I used batching to digest large data in Matlab before. Still wonder the answers to the two specifics questions without resorting to batching. Thanks. -Sean On Sat, Mar 14, 2009 at 10:13 PM, jim holtman wrote: > Exactly

Re: [R] Stuck on building a package

On 15/03/2009 4:46 AM, Ajay Shah wrote: Folks, I have a personal package which used to build fine. Today when I tried to build the package again, some errors popped up. Could you please help? Generally questions about building packages are better in R-devel. When I paste the offending funct

Re: [R] Help_Unable to run glmer

It's a 404 message. Try a repository that does have it. The CMU repository has a copy but the one you picked does not seem to have one at the moment. Maybe there was a run on the British bit and the bit banks are a wee short? http://lib.stat.cmu.edu/R/CRAN/bin/windows/contrib/2.8/ -- David

Re: [R] persp plot + plotting grid lines

This wiki page has the answer. Draw the plot first to establish the coordinate system and create the viewing transformation matrix. Draw the grid lines with lines(trans3d()), and then put a: par(new=T) ... and then redraw the plot over the gridlines.

[R] Help_Unable to run glmer

Can anyone help with this - I have been running glmer code for linear mixed models on my works pc, and am now working on my laptop (which is vista) and when I load the lme4 package i get the message below and I cannot run any models - any one have any ideas? Emma trying URL 'http://cran.uk.r-pr

Re: [R] Please help me to understand environments

You might want to look at rm to see how that function handles the problem. -- David Winsemius On Mar 15, 2009, at 3:14 AM, Ajay Shah wrote: I want to write: zap <- function(v) { if (exists(v)) {rm(v)} } But of course this doesn't work because the rm() acts on v which is within zap() and d

Re: [R] read.xls question

There are two read.xls functions: one is in gdata and one is in xlsReadWrite packages and neither is unreliable. You've simply not loaded the package. There is more info here and interfacing to Excel: http://wiki.r-project.org/rwiki/doku.php?id=tips:data-io:ms_windows You should read the Introd

Re: [R] cbind(NULL,zoo.object)?

I've just committed a fix to the zoo svn repository. You can grab it like this: source("http://r-forge.r-project.org/plugins/scmsvn/viewcvs.php/*checkout*/pkg/R/merge.zoo.R?rev=575&root=zoo";) On Sun, Mar 15, 2009 at 2:54 AM, Ajay Shah wrote: > Folks, > > I often build up R objects starting fro

Re: [R] read.xls question

To turn the function avaliable you have to load the library first, to do so: library(xlsReadWrite) Then you use your command read.xls. I'm suposing that you already had installed the xlsReadWrite package. A better alternative to this package is RODBC, which also read excel 2007 files. Take a

Re: [R] full screen graph, and close x11

thx , i will look that. I'm both on windows and linux 2009/3/12 Eik Vettorazzi > Hi, > see > ?dev.off > but I think (guessing you use a windows system), you would be better of in > using win.metafile() instead of x11() in initiating the graph, see > ?win.metafile > There is no need to show

[R] Stuck on building a package

Folks, I have a personal package which used to build fine. Today when I tried to build the package again, some errors popped up. Could you please help? When I paste the offending function into an R it works correctly. But the package build breaks. $ R CMD check ansecon * checking for working pdfl

Re: [R] dispcrepancy between aov F test and tukey contrasts results with mixed effects model

lba...@montana.edu wrote: Hello, I have some conflicting output from an aov summary and tukey contrasts with a mixed effects model I was hoping someone could clarify. I am comparing the abundance of a species across three willow stand types. Since I have 2 or 3 sites within a habitat I have in

Re: [R] read.xls question

On Sat, 14 Mar 2009, Mathew, Abraham T wrote: I'm an R newbie and had a question about the read.xls function. I've heard that this is often not a reliable function to use for importing data. However, I have created numerous xls files which contain information about voter turnout and macroecon

Re: [R] SEM model testing with identical goodness of fits (2)

Dear John, Thanks for the prompt reply! Sorry did not supply with more detailed information. The target model consists of three latent factors, general risk scale from Weber's domain risk scales, time perspective scale from Zimbardo(only future time oriented) and a travel risk attitude

[R] dispcrepancy between aov F test and tukey contrasts results with mixed effects model

Hello, I have some conflicting output from an aov summary and tukey contrasts with a mixed effects model I was hoping someone could clarify. I am comparing the abundance of a species across three willow stand types. Since I have 2 or 3 sites within a habitat I have included site as a random effe

[R] read.xls question

I'm an R newbie and had a question about the read.xls function. I've heard that this is often not a reliable function to use for importing data. However, I have created numerous xls files which contain information about voter turnout and macroeconomic indicators in India. I'm writing a paper on

[R] Please help me to understand environments

I want to write: zap <- function(v) { if (exists(v)) {rm(v)} } But of course this doesn't work because the rm() acts on v which is within zap() and doesn't affect the parent environment: > x <- 1 > zap("x") > x [1] 1 How would I make this zap() function work? -- Ajay Shah