Re: [R] identify with image

On Tue, 2 Sep 2003, Roger Bivand wrote: The simplest case is: plot(1:10) xy - list() identify(xy, n=1) Segmentation fault but identify(xy) Error in identify.default(xy) : invalid number of points in identify I'm not sure, but adding a check against zero-length and/or NULL x and or y

[R] glmmPQL probelm

Dear listers, First let me appologize if the same mail arrives multiple times. Recently I had some probelms sending my e-mails to the list. I encountered a problem when running glmmPQL procuedure doing multilevel modeling with a dichotomous outcome. Those are the two error messages I usually

Re: [R] glmmPQL probelm

Nothing to do with glmmPQL (as traceback() would have shown you). I think you are looking for ?try. On Wed, 3 Sep 2003, Andrej Kveder wrote: Dear listers, First let me appologize if the same mail arrives multiple times. Recently I had some probelms sending my e-mails to the list. I

[R] Course 'Bootstrap methods and permutation tests' - 23 - 24October

Insightful are pleased to announce we are now taking bookings for our latest course on Bootstrap methods and permutation tests in the UK on 23rd - 24th October. This course will focus in particular on two resampling methods, bootstrapping and permutation tests, which have been applied

[R] iinstallation R-grid-package

trying to install package R-grid on R vers. 1.7.0: # rpm -i R-grid-0.7.R4-1.i386.rpm file /usr/lib/R/library/grid/DESCRIPTION from install of R-grid-0.7.R4-1 conflicts with file from package R-base-1.7.0-1 file /usr/lib/R/library/grid/Meta/Rd.rds from install of R-grid-0.7.R4-1 conflicts

[R] Re: normal distribution in samples of soil organisms.

Hi, You didn't specify the satistical model you are intereted in, I will suppose it is something like: #Organims ~ Landscape + Soil + Depth + Species I suppose you have a table of with something like... SpecLands SoilDepth #Organisms A 1 1 1 10 A 1

[R] Matrix problem - possibly use of 'outer'

Hi, I can't get my head around this - can someone give me a pointer: I have a vector of values ('orig') representing areas and I want to calculate the amount contributed by each original vector values in a new vector ('new'). I find this hard to explain so here is a graphical explanation: #

Re: [R] How to avoid automatic coercion to factor?

On Tue, 2003-09-02 at 17:30, Dutky, Steve wrote: I have a function that manipulates a list of numeric and character components of equal length and wants to return a data.frame. EG, f-function() { a-list(Int1=1:5,Char1=letters[1:5],Char2=letters[6:10]) b-data.frame(a) }

Re: [R] Axis color

On Mon, 2003-09-01 at 09:42, [EMAIL PROTECTED] wrote: Hello, my question is if I have two axes in a graphics as I can put him a different color al axis and to the number of the scale. ? Thanks. Ruben I am not entirely sure if you want the actual axis lines and tick marks in different colors

[R] plotting a distribution curves

Hi, is there a way to plot distribution curves (say normal or chi sq etc) from within R? For example I looked up the *chisq family of functions but I'm not sure as to how I would use them to generate a plot of the chi sq distribution (for arbitrary d.o.f). Thanks,

[R] SNK-test

How can I perform a Student-Newman-Keuls-Test for multiple comparision of means in R? (I did not manage to find any specific function in the libraries) Jörg Peter Baresel Technische Universität München Institut für Ackerbau und INformatik im Pflanzenbau D-85354 Freising Lange Point 51

Re: [R] plotting a distribution curves

Hallo On 1 Sep 2003 at 16:25, Rajarshi Guha wrote: Hi, is there a way to plot distribution curves (say normal or chi sq etc) from within R? For example I looked up the *chisq family of functions but I'm not sure as to how I would use them to generate a plot of the chi sq

[R] variance components

Which possibilities are there in R for estimation of Variance components? Jörg Peter Baresel Technische Universität München Lehrstuhl für Pflanzenbau und Pflanzenzüchtung D-85354 Freising Lange Point 51 [[alternative HTML version deleted]]

RE: [R] plotting a distribution curves

-Original Message- From: Petr Pikal [mailto:[EMAIL PROTECTED] Sent: 03 September 2003 13:57 To: [EMAIL PROTECTED] Cc: [EMAIL PROTECTED] Subject: Re: [R] plotting a distribution curves Hallo On 1 Sep 2003 at 16:25, Rajarshi Guha wrote: Hi, is there a way to plot

Re: [R] plotting a distribution curves

Petr Pikal [EMAIL PROTECTED] writes: Hallo On 1 Sep 2003 at 16:25, Rajarshi Guha wrote: Hi, is there a way to plot distribution curves (say normal or chi sq etc) from within R? For example I looked up the *chisq family of functions but I'm not sure as to how I would use

RE: [R] variance components

Use the nlme( ) package: library(nlme) The lme( ) and nlme( ) functions in this package are designed to estimate mixed effects models. An outstanding reference is Mixed Effects Models in S and Splus, by Drs. Pinheiro and Bates. Best, david paul -Original Message- From: Jörg Peter

[R] problem with HoltWinters

Dear helpers I'm having a problem with function HoltWinters from package ts. I have a time series that I want to fit an Holt-Winters model and make predictions for the next values. I've already built an object of class ts to serve as input to HoltWinters. But then I get an error; I've used

Re: [R] Another R syntax question

On Wed, 3 Sep 2003, Richard A. O'Keefe wrote: The file src/library/base/R/print.R contains this line: x0 - xm[okP]==0 != (as.numeric(Cf[okP])==0) I didn't know R allowed that, and I wonder if it is deliberate? Well, I'm not surprised that it's syntactically valid, but I wouldn't know

Re: [R] Another R syntax question

Thomas Lumley [EMAIL PROTECTED] writes: I think it's clear that it will parse as either (x==y) != z or x == (y!=z) but not which. The rule is that everything is left associative except assignment and exponentiation (and IF, for some reason). If in doubt, just remember that it is the

[R] Call R function from C code

I am participating in a project in the university, and appeared a doubt: if can I call one function from R as solve from C code. The intention of the research is to create a DLL. Is it possible and where can I find an example? Sorry for bad english!

Re: [R] Call R function from C code

Dear Fabio, This question, or one very much like it, appears regularly on the list. You may consider searching for it in the archives before going much further. The search page can be found at http://cran.r-project.org/search.html. Regards, Andrew C. Ward CAPE Centre Department of Chemical

RE: [R] I don't understand this

Thanks to everyone for enlightening me about (f)(g). So I suppose (f)(g)(h)... is OK as long as (f)(g) returns a function with an argument (and so on)? Meanwhile, back on Earth, in attempting a compromise between the clarity of Barry R's if (cond) names(x) - 10 else dim(x) - 10 and the

[R] Diagnostic tool for s.window in the STL method for Time seriesAnalysis

Dear R-Help, 1. Does somebody know a diagnostic tool to determine the n(s), smoothing parameter of the seasonal component in the STL method for Time Series? s.window= n(s)= smoothing parameter Is tsdiag the solution? If yes how can it be used? Should I use arima or StructTS? 2. Also does the

Re: [R] I don't understand this

Simon Fear wrote: foo(x) - 10 Error: couldn't find function foo- this is because you defined 'foo', and not 'foo-', which are two different functions. if instead (or as well) you did: foo- - if (TRUE) get(names-) else get(dim-) then it works. Doesn't cure this one though: (foo)(x) - 10

Re: [R] I don't understand this

Richard A. O'Keefe [EMAIL PROTECTED] writes: Thomas Lumley [EMAIL PROTECTED] wrote: I would have said that the behavior of (if (cond) names else dim)(x) - 10 is undefined in the S language, along with things like the order of evaluation of the apply functions.

Re: [R] SNK-test

Have you tried www.r-project.org - search - R site search? I just got several hits for multiple comparisons and Newman-Keuls. hope this helps. spencer graves Jörg Peter Baresel wrote: How can I perform a Student-Newman-Keuls-Test for multiple comparision of means in R? (I did not manage to

RE: [R] I don't understand this

On Wed, 3 Sep 2003, Simon Fear wrote: Thanks to everyone for enlightening me about (f)(g). So I suppose (f)(g)(h)... is OK as long as (f)(g) returns a function with an argument (and so on)? Indeed. As an example of what can be done recurse - function(f) { g- function(h)

Re: [R] How to avoid automatic coercion to factor?

Steve Dutky [EMAIL PROTECTED] wrote: I have a function that manipulates a list of numeric and character components of equal length and wants to return a data.frame. ... How can I get the columns Char1, Char2, (...CharN) returned coerced to character and not factor? Prof Brian Ripley [EMAIL

Re: [R] replot

On Wed, 2003-09-03 at 10:39, [EMAIL PROTECTED] wrote: Hi, how i cant replot a graphics, te function replot() not exist in R for win 1.7.1, how i cant without plot.new? In general, you need to simply re-execute the function or series of functions (with any changes) to re-display a plot. There

Re: [R] problem with HoltWinters

HoltWinters() by default fits a seasonal model, and therefore needs three complete cycles for the starting values. But your third cycle is incomplete, so in short, you haven't got enough data to fit a seasonal model, unless you provide all starting values using l.start, b.start, and s.start. I

[R] boot package

Hi, I'm getting this error that I don't understand can someone give an hint on this ? Thanks EJ boot.ci(blm01,type=bca,index=4) Error in if (const(t, min(1e-08, mean(t)/1e+06))) { : missing value where TRUE/FALSE needed __ [EMAIL PROTECTED]

[R] ANN: An XML format for block designs

A standard format for block designs and their properties (A proposal and an invitation for public debate) At DesignTheory.org we are developing a web-based Design Theory Resource Server for combinatorial and statistical

Re: [R] I don't understand this

On Wed, 3 Sep 2003, Richard A. O'Keefe wrote: Another assignment-related thing I'm not clear on is what f(x) - e is supposed to do. Me neither. f(x) - e is equivalent to x - f-(x, value=e) and x - e assigns to x in the next outer environment, but a simple

[R] Overlaying graphs

I am wanting to construct a probability distribution for height and then, hopefully, visually and analytically demonstrate that it is normally distributed. These are the commands I have developed so far: fat - read.table(fat.dat, header=TRUE) mu- mean(fat$height) sdev - sd(fat$height)

[R] impact of R and S

It is interesting how things have changed -- 5 weeks later, I review materials collected at the JSM, and notice that Springer-Verlag's glossy statistics catalog has 3 of 9 books on the front page directly or indirectly related to R (Peter D's intro book, MASS, and Parmigiani et.al's book with a

Re: [R] llines and NA

This is a bug in grid.lines. A possible workaround is to use your own function that handles this using grid.segments (or lsegments). On Wednesday 03 September 2003 09:09 am, Bodo Ahrens wrote: Hallo helpers, I tried to use llines of package lattice in e.g. levelplot(z~x+y,xyz,

[R] lme in R and Splus

Good Day, Included below is some code to generate data and to fit a mixed effects model to this fake data. The code works as expected when I call the function lme in Splus but not in R. The error message from calling lme in R is: Error in getGroups.data.frame(dataMix, groups) :

[R] plot only partial plots

Hi everybody, I would like to plot only a part of a data frame, and identify the IDs for all the points with values higher than a certain value. I will try to be more explicit: I did a qqnorm plot of my data. It is obvious from the plot that all the sample quantiles which are in Theoretical

Re: [R] boot package

It's hard to say, but I sometimes get this error when I either have a very small dataset or if I don't do enough resamples (i.e. R is too small). -roger Ernesto Jardim wrote: Hi, I'm getting this error that I don't understand can someone give an hint on this ? Thanks EJ

Re: [R] plot only partial plots

I don't know about doing it all on the same line, but have you considered something like the following: DF - data.frame(x=1:9, y=1:9, z=rep(1:3, 3)) plot(DF$x, DF$y, type=n) sel - (DF$z2) text(DF$x[sel], DF$y[sel], letters[1:3]) hope this helps. spencer graves Monica Palaseanu-Lovejoy wrote:

Re: [R] Overlaying graphs

Paul Meagher [EMAIL PROTECTED] writes: I am wanting to construct a probability distribution for height and then, hopefully, visually and analytically demonstrate that it is normally distributed. These are the commands I have developed so far: fat - read.table(fat.dat, header=TRUE) mu

Re: [R] lme in R and Splus

Michael Fugate [EMAIL PROTECTED] writes: ## BEGINNING OF CODE ### # a fake dataset to make the bumps with nn - 30 # of data points mm - 7 # number of support sites for x(s) # create sites s ss - seq(1,10,length=nn) # create the data y e1 -

Re: [R] value of hypsometric integral ( ecdf() )

On 3 Sep 2003 at 17:31, Rado Bonk wrote: ? It is not really clear what you want, since what you call the hypsometric curve is really the cumulative distribution function, so its integral is infinite. Does the following help? data(volcano) library(stepfun) plot(ecdf(volcano), do.points=F,

Re: [R] lme in R and Splus

Michael Fugate [EMAIL PROTECTED] writes: ## BEGINNING OF CODE ### # a fake dataset to make the bumps with nn - 30 # of data points mm - 7 # number of support sites for x(s) # create sites s ss - seq(1,10,length=nn) # create the data y e1 -

[R] Calling functions of R from Perl?

Hi, I've already asked this question, but unfortunately I've combined it with another question. So it was ignored in almost all cases. Thanks to those who have already given some hints. Here again: I don't want to use R interactively (issue commands after the prompt ..), but use some

RE: [R] How to avoid automatic coercion to factor?

Prof Brian Ripley [EMAIL PROTECTED] wrote: ... If you really want character columns, the way to do it is underhand: f - function() { a - list(Int1=1:5,Char1=letters[1:5],Char2=letters[6:10]) attr(a, row.names) - 1:5 attr(a, class) - data.frame a } ... This certainly appears to me

Re: [R] Calling functions of R from Perl?

On Wed, Sep 03, 2003 at 11:13:30PM +0200, Bernhard Bals wrote: I don't want to use R interactively (issue commands after the prompt ..), but use some functionality of R from inside a Perl script. Can I use methods of R from a Perl script: Is there an interface from Perl (or at least from

Re: [R] help.start( )

On Wed, 2003-09-03 at 17:41, Ming wrote: Dear R experts, I installed R-1.7.1 on Linux (Red Hat 9.0) starting from R-1.7.1.tgz without a problem. Then I fired up R and tried things and found that help.start( ) does not work. I downloaded Sun Java j2re1.4.2, installed that and re-installed

[R] carma (package growth)

Dear helpers, I am wondering if I can use the growth package to fit continuous ARMA time series. To be specific, y - arima.sim(model=list(ar=c(1.7,-0.8)),n=100) How do I use carma to fit y if possible? The package is for longitudinal data but I suspect I can use it for my problem. I looked at