Re: [R] off-topic: better OS for statistical computing

insight. > Have a nice day. Linux. It's best for ***everything***. cheers, Rolf Turner ## Attention:\ This e-mail message is privileged

Re: [R] computing distance in miles or km between 2 street addre

ses > in the database. > > As far as I know, R has no > database relevant to street addresses! But Ted! Don't you know that statistics in general and R in particular are

Re: [R] Help on inverse distribution

On 5/09/2007, at 11:16 AM, Lisa Hu wrote: > To make it specific, I need to simulation Y with inverse beta > distribution, > that is, Y~inverseF(X), where F is the CDF of beta distribution. > THANKS > > On 9/4/07, Lisa Hu <[EMAIL PROTECTED]> wrote: >> >> Dear All, >> >> I need to use the inver

Re: [R] Pie Chart Labels

On 5/09/2007, at 9:37 AM, Greg Snow wrote: > The best option is to use a bar chart or dot chart instead of a pie > chart. Right on, Red Freak!!! :-) cheers, Rolf

Re: [R] Excel

learn astrology? cheers, Rolf Turner ## Attention:\ This e-mail message is privileged and confidenti...{{dropped}} __ R-help@stat.math.eth

Re: [R] piecewise linear approximation

bit. The argument ``b'' to the bsr() function is a vector of candidate values for the ``join point'', e.g. b <- seq(lo,hi,length=100), where lo and hi are suitably chosen lower and upper bounds on the location of the join point. cheers,

[R] Linear modelling confusion.

time to read this long-winded cri de coeur. If anyone is actually *interested* I would be very happy to make the data available to her or him. cheers, Rolf Turner ## Attention:\ This e-m

Re: [R] combining datasets by row

eturn a value*. The write.csv call should be ``done to this value'', outside of the cleanup_data() function. IMHO. A sexier way to do what you want would be: cleanup_data <- function(state,count) {

Re: [R] a new-bie question about obtaining certain value from the print out

ded"; the c() function is for ``combine'' or ``catenate''. You don't need to ``combine'' a single item! The wrapper does no harm, but it's a waste of key strokes and indicates a certain lack of insight which *could* do harm in more complex situatio

Re: [R] Excel

has made it > easier. Bravo!!! Very well and very cogently expressed! cheers, Rolf Turner ## Attention:\ This e-mail message is privileged and conf

Re: [R] Excel

commentary on Excel, available at the URL: http://www.stat.uiowa.edu/~jcryer/JSMTalk2001.pdf Executive summary: Friends don't let friends use Excel for statistics. cheers,

Re: [R] Choice of data.frame column by index?

On 24/08/2007, at 12:51 PM, Moshe Olshansky wrote: > This won't work since it produces a matrix (try this). On the contrary, Patrick's solution is correct. I tried it. It works just fine. cheers, Rolf Turner

Re: [R] tackle memory insufficiency for large dataset using save() & load()?

1]. These R Core people are sneaky-clever! cheers, Rolf Turner ## Attention:\ This e-mail message is privileged and confidenti...{{dropped}} ___

Re: [R] tackle memory insufficiency for large dataset using save() & load()?

ish the same thing. cheers, Rolf Turner ## Attention:\ This e-mail message is privileged and confidenti...{{dropped}} __ R-help@stat.math.e

Re: [R] (Most efficient) way to make random sequences of random sequences

On 22/08/2007, at 8:49 AM, Emmanuel Levy wrote: > Hi, > > I was wondering the what would be the (most efficient) way to generate > a sequence > of sequences, i mean: > > if I have 1,2 and 3. > > I'd like to generate a sequence of length N*3 (N ~ 1,000,000 or more) > > Where random permutations of

Re: [R] small issue with densityplot

cheers, Rolf ## Attention:\ This e-mail message is privileged and confidenti...{{dropped}} __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailma

Re: [R] Does anyone.... worth a warning?!? No warning at all

,2,3) returns ``2'' --- just as max (1,2,3) returns ``3'' --- as Mathew *initially* (and quite reasonably) expected it to do. cheers, Rolf Turner

Re: [R] Covariance of data with missing values.

Thank you ***very*** much Ted and Chuck. I will install these two packages and study them over, and then in all probability pester you with more questions when I find things that I don't understand! Thanks again. cheers, Rolf

[R] Covariance of data with missing values.

nks for any pointers that anyone may be able to give. cheers, Rolf Turner ## Attention:\ This e-mail message is privileged a

Re: [R] time series periodic data

er Bloomfield's book (``Fourier Analysis of Time Series: An Introduction'', 2nd ed., Wiley, 2000) for a good introduction to complex demodulation. cheers, Rolf Turner

Re: [R] CDF of a gamma distribution

On 15/08/2007, at 9:53 AM, Jake Verschuyl wrote: > I have some bird flight height data that follows a gamma > distribution. The > data (x) goes from 0 to 700 meters (n=1055). The calculated > parameters > calculated from the fitdistr(x) are (shape = 5.1379, rate = > 0.017541), and > there

Re: [R] Colours in R, was: deldir package - voronoi

On 13/08/2007, at 11:27 AM, Wolfgang Huber wrote: > Dear Rolf and Binabina > > perhaps this is of use to some: > > Colour for Presentation Graphics. Ross Ihaka. > www.stat.auckland.ac.nz/~ihaka/colour/color.pdf > > Choosing Color Palettes for Statistical Graphics > Ac

[R] The deldir package.

a considerable improvement to the algorithm used to produce the tile list. The bug was pointed out to me by Majid Yazdani, to whom I express my sincere thanks. cheers, Rolf Turner

Re: [R] deldir package - voronoi

re just *how* they relate. With a bit of luck, someone cleverer than I will come to your rescue. cheers, Rolf Turner ## Attention:\ This

Re: [R] small sample techniques

e of this is however germane to Nair's original question; it is clear that he is interested in a two-independent-sample t-test. cheers, Rolf Turner #

Re: [R] manipulating arrays

?append cheers, Rolf Turner On 28/07/2007, at 2:12 AM, Henrique Dallazuanna wrote: > Hi, I don't know if is the more elegant way, but: > > X<-c(1,2,3,4,5) > X <- c(X[1], 0, X[2:5]) > > > -- > Henrique Dallazuanna > Curitiba-Paran

Re: [R] spatstat - Fitting a Strauss model with trend determined by kernel density smoother

e 42 in the forgoing example); this radius is an ``irregular'' parameter --- i.e. it does not appear in exponential family form --- and hence is not estimated by ppm(), at least not directly. cheers,

Re: [R] for loop doesn't stop with upper loop value

o precedence of operators (this ain't APL) o parentheses are Good Things. cheers, Rolf Turner ## Attention:\ This e-mail message is privilege

Re: [R] generating correlated Bernoulli random variables

Typo in my previous email: sqrt((1-p1)*(1-p2)) should have read sqrt(p1*(1-p1)*p2*(1-p2)) I think! cheers, Rolf ## Attention:\ This e-mail message is privileged

Re: [R] generating correlated Bernoulli random variables

e of rho (in terms of p1 and p2) in order that the values of q1 and q2 lie between 0 and 1. I.e. for some values of rho your goal will be impossible to achieve. cheers,

Re: [R] Extracting sums for individual factors in data frames

?tapply ## Attention:\ This e-mail message is privileged and confidenti...{{dropped}} __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do re

[R] Catenating factors.

of the levels of x and y? I vaguely recall seeing this discussed in r-help, but I can't find anything on it there, nor in the FAQ. Am I missing something obvious? cheers, Rolf [EMAIL PROT

Re: [R] quartz() on MAC OSX

On 22/5/07 6:48 AM, "hadley wickham" <[EMAIL PROTECTED]> wrote: > Hi Rolf, > > Two possible solutions: > > * DISPLAY=0.0.0.0:0 R - and then X11() should work without having to use > xterm > > * install.packages("CarbonEL"); library(Carbon

[R] quartz() on MAC OSX

to get a working on-screen graphics window under these circumstances? I am very much hand-cuffed by the officious ITS policies here as to what I can install on my Mac. (Effectively, nothing.) ``cheers'' (Hah!),

Re: [R] S-plus coding

T. Kounouni wrote: > Hi, how can i use data to forecast next time period value, if data > has been influenced by a change in legislation? thank you. Well, you could use chicken entrails. cheers, Rolf

Re: [R] Too slow to execute!

dded that ``Re'' is not a good name for an object since it is the name of a function (which returns the real part of complex numbers). cheers, Rolf Turner [E

Re: [R] A coding question involving variable assignments in ifelse()

heers, Rolf Turner [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-projec

Re: [R] regarding 3d Bar Plot --- correction.

odall actually wrote to see if it could be useful to guarav. cheers, Rolf Turner [EMAIL PROTECTED] __ R-help@stat.math.ethz.ch mailing list

Re: [R] regarding 3d Bar Plot

call to segmtz changed to a call to segments() --- but this would seem to be a lot of work. Can anyone suggest a reasonably simple way of replacing the call to segmtz in the Fortran? cheers

Re: [R] Open source community help-desks

an say `Existence exists' with a straight face is either a fool or a charlatan.'' cheers, Rolf Turner [EMAIL PROTECTED] ___

Re: [R] Estimating a Normal Mixture Distribution

p[5] p<-p[1] colSums(attr(lmix2a(x,p,u1,s1,u2,s2),"gradient"))} then your procedure seems to work --- at least it gives an answer different from the starting values. cheers, Rolf Turner

Re: [R] Opinion on R plots: connecting X and Y

I would say ``de gustibus non disputandum'', except that I can't speak Latin. cheers, Rolf Turner [EMAIL PROTECTED] __ R-help@stat.math.ethz.ch mai

Re: [R] hello

at one was expecting or wanting. However you *can* get what you want: > as.numeric(as.character(f)) [1] 2 4 6 8 10 2 4 6 8 10 2 4 6 8 10 cheers, Rolf Turner

Re: [R] how to reverse a list

ctor*, not a list. Don't use a chainsaw when you need a fretsaw. cheers, Rolf Turner [EMAIL PROTECTED] __ R-help@stat.math.ethz.ch maili

Re: [R] Referencing function name from within function

uires xyz! > lapply(1:10,myfunction) Error in FUN(c(1, 2, 3, 4, 5, 6, 7, 8, 9, 10)[[1]], ...) : myfunction requires xyz! cheers, Rolf Turner

Re: [R] Referencing function name from within function

(paste(nm,"requires xyz!")) } } cheers, Rolf Turner [EMAIL PROTECTED] ===+===+===+===+===+===+===+===+===+===+===+===+===+===+===+===+===+===+=

Re: [R] Doing partial-f test for stepwise regression

Not that it really matters --- the anova() function gives you the same F statistic and p-value either way. And the negative SS is a dead giveaway that something is a bit skew-wiff. cheers, Rolf Turner

Re: [R] Query about substituting characters in a df

r to do with your problem. The following may give you the right idea: > xxx <- sample(1:10,100,TRUE) > yyy <- letters[1:10][match(xxx,1:10)] cheers, Rolf Turner

Re: [R] meta-regression, MiMa function, and R-squared

Hey, didn't Will Rogers say ``I never met a regression I didn't like?'' (Sorry 'bout that; couldn't resist.) cheers, Rolf Turner

Re: [R] sending a vector of characters as arguments for a function

s get lost. colnames(m) <- s0 # So tack them on. cheers, Rolf Turner [EMAIL PROTECTED] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-h

Re: [R] significant anova but no distinct groups ?

there will be at least one ``contrast'' amongst the means that is significantly different from zero on an a posteriori basis. This contrast need not however be a pairwise difference between means. cheers, R

Re: [R] nlm() problem : extra parameters

erences to ``n'' in the body of derfs4 by references to ``size'') then nlm() will work (?) --- but it seems to take 337 iterations, r.t. 3 (!!!) to converge. No idea what the problem is. cheers, Rolf Turner ===+===+===+===+=

[R] Documenting options specific to a package.

as to how and where the option ``melvin'' should be documented? It seems somewhat redundant to include docmentation about melvin in the help on all 4 of foo(), bar(), clyde(), and irving(). Thanks for any insights. cheers,

Re: [R] printing intermediate lines while in a function

You're using Windoze, aren't you? You didn't say. See the Windoze-specific FAQ, 7.1. cheers, Rolf Turner [

Re: [R] integrate over polygon

# of the bounding box of the polygon. spatstat.options(oop) # Set npixel back to the default. HTH. cheers, Rolf Turner [EMAIL PROTECTED] __

Re: [R] Newbie: Acf function

rrelogram'' and ``n.ecc'' is the length of the series from which ecc was created. Note that the first entry of ecc should be 1; it corresponds to lag 0. cheers, Rolf Turner

Re: [R] Beginner Question on Persp()

Your ``z'' which was read in by read.delim() is a *data frame* not a matrix. Do z <- as.matrix(z), then persp(x,y,z) will work. cheers, Rolf Turner [EM

Re: [R] Estimation of discrete unimodal density

ith reference) for the estimation of > univariate discrete unimodal densities (with unknown mode)? Thanks in > advance for your help. You could have a look at my ``isotonic'' package. Go to: http://www.math.unb.ca/~rolf/Research/Packages/ Click on ``gzi

Re: [R] what is the purpose of an error message in uniroot?

results about which he/she is deluded. cheers, Rolf Turner [EMAIL PROTECTED] P. S. If the f() values are of the same sign, uniroot() DOES NOT give a warning!

Re: [R] ifelse on data frames

lue = 0) : only logical matrix subscripts are allowed in replacement > > > > which changes NaN's to zeroes > > > > HTH > > Petr cheers, Rolf Turner

Re: [R] understanding integer divide (%/%)

Thierry Onkelinx wrote: > If you want to do an integer divide, you should only use integers to > divide with. I think this should go into ``fortunes''. cheers,

Re: [R] why are my multiple box & whisker plots so small?

f which is indicated in the help, which I suggest you read. > I've also tried using "plt" to make the plot area bigger, but this > has no effect either. If things don't fit, they don't fit. Wonderful as it is, R can't work mag

Re: [R] Summary shows wrong maximum

understood. Relying on an obscure convention is fraught with risk. cheers, Rolf Turner [EMAIL PROTECTED] __ R-help@stat.math.ethz

Re: [R] prop.trend.test issue

> I hope people's lives are not at stake with the results of your analysis Amen, brother. Well said. Another response springs to *my* mind but it is just as well to suppress it. cheers,

Re: [R] automatic cleaning of workspace

invisible() } Usage: clean() cheers, Rolf Turner [EMAIL PROTECTED] P. S. Moral of the story: If you want to do something in R and the facility is not built in, it is usually

[R] OT: P(Z <= -1.46).

cheers, Rolf Turner [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-guid

Re: [R] help

The word ``help'' does NOT constitute an informative subject line. cheers, Rolf Turner [EMAIL PROTECTED] __ R-help@stat.math.ethz.ch mailing

Re: [R] the secret (?) language of lists

ou already know the answer to your question. cheers, Rolf Turner [EMAIL PROTECTED] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEA

Re: [R] Plot title with numeric variables

Or to take a simpler and clearer example: > N <- 5 > plot(1:10,main=bquote("Figure"~.(N)) cheers, Rolf Turner [EMAIL PROTECTED] __

Re: [R] Making a case for using R in Academia

cheers, Rolf Turner [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://ww

Re: [R] How to Trace Back the Warning Messages

ers, Rolf Turner [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 commen

Re: [R] Worm distribution :-)

b) re-invention of the wheel. As I pointed out in a previous posting to the list there are a brazillion ways of generating point patterns with interpoint inhibition, readily available in R. cheers,

Re: [R] Worm distribution :-)

there is a variety of ways to simulate ``regular'' random point patterns --- rMaternI, rMaternII, rSSI, and rmh (which simulates several point pattern models depending on the specified Papangelou conditional intensity function). cheers,

Re: [R] Re : Generate a random bistochastic matrix

y guess is that it would be a hard problem. cheers, Rolf Turner [EMAIL PROTECTED] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.c

Re: [R] generate random numbers that sum up to 1

As I have previously asked, in response to a similar question: Is this a homework problem? cheers, Rolf Turner [EMAIL PROTECTED] __ R-help@stat.math.ethz.ch

Re: [R] Block comments in R?

(It's one of the --- many --- reasons I like R better than Splus, which I no longer use.) Changing the R documentation system to something (Monty?) Pythonesque would change the nature of R and make it uglier.

Re: [R] ifelse(logical, function1, function2) does not work

rep.function() *explicitly* I got what I wanted. I.e. > rep.function(sin,5) gave a list of length 5 each entry of which was ``.Primitive("sin")''. Questions: How do methods for rep() get dispatc

Re: [R] setting the environment variable R_LIBS

/library export R_LIBS HTH. cheers, Rolf Turner [EMAIL PROTECTED] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help

Re: [R] How can I generate this numbers

Ricardo Rios wrote: > Hi Rolf Turner, I have a statistical model, it model need this > numbers for calculate the probability. This numbers must be random. > > For example I need that > >magicfunction(3) > >[1] 0.3152460 0.5231614 0.1615926 > >magicfunction(

Re: [R] How can I generate this numbers

This sounds so simple it must be a homework problem, no? cheers, Rolf Turner [EMAIL PROTECTED] __ R-help@stat.math.ethz.ch mailing list

Re: [R] Print/Save/Cat/Write list

?sink __ 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] "unvector" ?

quot; works, but this amounts to playing an unnecessary game of ring-around-the-rosy. cheers, Rolf Turner [EMAIL PROTECTED] __ R-help@stat.math.ethz.ch ma

Re: [R] Matrix multiplication using apply() or lappy() ?

i in 1:1) junk <- t(t(a)/a[1,])) [1] 5.530 0.940 7.856 0.000 0.000 cheers, Rolf Turner __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read th

Re: [R] write a table to file with unequal length of lists

"ddd.out",quote=FALSE,row.names=FALSE) cheers, Rolf Turner [EMAIL PROTECTED] Original message: > Dear R helpers, > > To illustrate my problem, here is a simplified example. I

[R] Summary --- Local library under Windoze.

this library: library("foo",lib.loc="lnilp") (where ``lnilp'' means ``library not in library path''). BTW, lib.loc can be specified by the *relative* path name, with no problem. Thanks to all.

[R] Local library under Windoze.

bind",lib="Lib") Everything went according to form (I got prompted to choose a mirror, etc.) until the end of the show when I got the warning message Warning: unable to move temporary installation 'C:\Documents and Settings\rolf\My Documents\Rstuff\Lib\file5f906952\Lib\file5f90

[R] Summary and thanks: .Rprofile under Windoze.

n file types'' and clicking on ``Apply to All Folders''. Thanks again to everyone. cheers, Rolf Turner [EMAIL PROTECTED] __

[R] .Rprofile under Windoze.

eds to be clarified under Windoze. Following the suggestions in An Introduction to R, I tried putting a .Rprofile in "C:\Documents and Settings\rolf\My Documents" When that didn't work, I tried putting it in the starting directory (and confirmed that I'd got that

Re: [R] Adding a footnote in plot-window in R

?legend __ 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] fitting a gaussian to some x,y data

illustrates the point that you really shouldn't be *doing* statistics unless you *understand* some statistics. At the very best you'll waste a great deal of time. cheers, Rolf Turner

Re: [R] Creating a pixel image

ing the ``bandwidth'' parameter sigma for the smooth is however a bit of a mystery, apparently even to the cognoscenti. cheers, Rolf Turner [EMAIL PROTECTED]

Re: [R] "model = F" causing error in polr()

Try ``model = FALSE'' rather than ``model = F'' and see if it makes a difference. You make have an unwanted variable named ``F'' lurking somewhere. (In general it is a *bad* idea to use ``F'' when ``FALSE'' is intended.)

Re: [R] OT UNIX grep question

#x27;' error. To protect against the shell interpretation of the dollar sign you have to use *single* quotes. grep '^dog$' /usr/share/dict/words *does* work. (Try it!) cheers, Rolf Tur

Re: [R] minimization a quadratic form with some coef fixed and some constrained

b = (M_11)^{-1}c cheers, Rolf Turner [EMAIL PROTECTED] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do rea

Re: [R] Comparison of linear models

d the nature of ``factors''. John Fox's book ``Applied Regression Analysis, Linear Models, and Related Methods'' might be a reasonable place to start. Bon chance. cheers, Rolf T

Re: [R] information about a function

ou created does the calculations for you; all you would be doing is reinventing the wheel. cheers, Rolf Turner [EMAIL PROTECTED] __ R-help@stat.math.ethz.ch mai

Re: [R] Invoke operating system command

?system __ 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

Re: [R] modeling logit(y/n) using lrm

has columns named ``y'' ``n'' and whatever the predictors are called. cheers, Rolf Turner [EMAIL PROTECTED] __ R-help@stat.

Re: [R] if syntax error :(

;'. Use ``plot=FALSE''. (Note that the symbols ``F'' and ``T'' are assignable, *unlike* ``TRUE'' and ``FALSE''.) cheers, Rolf Turner [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

Re: [R] Density Estimation

n(): > spiffy <- splinefun(kde$x,kde$y) > integrate(spiffy,0,3) 0.2353400 with absolute error < 2e-09 cheers, Rolf Turner [EMAIL PROTECTED] __ R-help@stat.math.ethz.c

  1   2   3   4   >