Re: [R] Fitting models in a loop

2006-07-31 Thread Bill.Venables
Murray, Here is a general paradigm I tend to use for such problems. It extends to fairly general model sequences, including different responses, c First a couple of tiny, tricky but useful functions: subst - function(Command, ...) do.call(substitute, list(Command, list(...))) abut -

Re: [R] Fitting models in a loop

2006-08-01 Thread Bill.Venables
Markus Gesmann writes: Murray, How about creating an empty list and filling it during your loop: mod - list() for (i in 1:6) { mod[[i]] - lm(y ~ poly(x,i)) print(summary(mod[[i]])) } All your models are than stored in one object and you can use lapply to

Re: [R] Fitting models in a loop

2006-08-01 Thread Bill.Venables
This (below) also runs into trouble if you try to predict with new data since you have no rule for re-constructing the formula. Also, you can't plot the term as a single contributor to the linear predictor with termplot(). I'm sure given enough ingenuity you can get round these two, but why

Re: [R] Constrain coefs. in linear model to sum to 0

2006-08-07 Thread Bill.Venables
Gorjanc Gregor asks: Hello! I would like to use constrain to sum coeficients of a factor to 0 instead of classical corner contraint i.e. I would like to fit a model like lm(y ~ 1 + effectA + effectB) and say get parameters intercept effectA_1 effectA_2 effectB_1 effectB_2

Re: [R] Help with workaround for: Function '`[`' is not in thederivatives table

2006-08-15 Thread Bill.Venables
Earl F. Glynn asks: -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Earl F. Glynn Sent: Tuesday, 15 August 2006 8:44 AM To: r-help@stat.math.ethz.ch Subject: [R] Help with workaround for: Function '`[`' is not in thederivatives table # This works

Re: [R] glm inside one self-defined function

2006-08-22 Thread Bill.Venables
Mike Wolfgang asks: From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Mike Wolfgang Sent: Wednesday, 23 August 2006 1:31 PM To: R-help list Subject: [R] glm inside one self-defined function Hi list, I've searched in R-help and found some related discussions but still could

Re: [R] Check values in colums matrix

2006-08-24 Thread Bill.Venables
As a minor footnote to both of these, I would add that both assume that all the columns of the dataset are numeric. It doesn't cost much to generalize it to cover any matrix structure, of any mode: constantColmuns - function(Xmat) which(apply(Xmat, 2, function(z) length(unique(z)) == 1))

Re: [R] singular matrix

2006-08-28 Thread Bill.Venables
Nongluck Klibbua reports: -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Nongluck Klibbua Sent: Tuesday, 29 August 2006 11:12 AM To: R-help@stat.math.ethz.ch Subject: [R] singular matrix Dear R-users, I try to use solve to get the solution

Re: [R] Type II and III sum of square in Anova (R, car package)

2006-08-29 Thread Bill.Venables
I cannot resist a very brief entry into this old and seemingly immortal issue, but I will be very brief, I promise! Amasco Miralisus suggests: As I understood form R FAQ, there is disagreement among Statisticians which SS to use

RE: [R] AIC, glm, lognormal distribution

2004-12-12 Thread Bill.Venables
Benjamin, A couple of points: fit - glm(y ~ x, gaussian(link = log)) does NOT fit a model with a lognormal response distribution. It fits a non-linear regression model with an ordinary gaussian response distribution. This model has constant variance, whereas the lognormal model (which you

RE: [R] A rude question

2005-01-27 Thread Bill.Venables
When Haydn was asked about his 100+ symphonies he is reputed to have replied sunt mala bona mixta which is kind of dog latin for There are good ones and bad ones all mixed together. It's certainly the same with R packages so to continue the latin motif: caveat emptor The R engine, on the other

RE: [R] error with polr()

2005-03-21 Thread Bill.Venables
This is always tricky. Here is a work-around. Try asking for the Hessian with the original fit: fm - polr(factor(y) ~ lx, data = ord.dat, Hess=T) summary(fm) Call: polr(formula = factor(y) ~ lx, data = ord.dat, Hess = T) Coefficients: Value Std. Error t value lx 2.420614 0.8146359

RE: [R] Robust multivariate regression with rlm

2005-03-23 Thread Bill.Venables
lm works for multivariate responses rlm does not - check what the help file says about the response. That's about it, really. Bill Venables. -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Markku Mielityinen Sent: Thursday, 24 March 2005 5:20 PM To:

RE: [R] Generating list of vector coordinates

2005-03-28 Thread Bill.Venables
rev(expand.grid(k = 1:5, j = 1:4, i = 1:3)) i j k 1 1 1 1 2 1 1 2 3 1 1 3 4 1 1 4 5 1 1 5 6 1 2 1 7 1 2 2 8 1 2 3 ... 55 3 3 5 56 3 4 1 57 3 4 2 58 3 4 3 59 3 4 4 60 3 4 5 -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Ronnen Levinson

RE: [R] NA's?

2005-03-30 Thread Bill.Venables
Your message doesn't help us very much. You haven't said what kind of calculation it is you want to do, and that certainly matters. For example, for some kinds of computations the solution you started below would work fine: M - matrix(1:16, 4, 4) is.na(diag(M)) - TRUE M [,1] [,2] [,3]

RE: [R] NA's?

2005-03-30 Thread Bill.Venables
is.na(diag(M)) - TRUE cmeans - colMeans(M, na.rm = TRUE) csd - apply(M, 2, sd, na.rm = TRUE) cvar - csd ^2 (or cvar - apply(M, 2, var, na.rm = TRUE) ) Using 'kmeans' on a matrix but 'ignoring the diagonal entries' just doesn't make sense as it stands, so I can't help you there. V.

RE: [R] how to draw a 45 degree line on qqnorm() plot?

2005-04-02 Thread Bill.Venables
You didn't try very hard. Try this, look at it and think about it: jj - scale(sample(1:100, 10)) qqnorm(jj) abline(0, 1) Rather than abline, however, most people, however, would use qqline(jj) in which case you don't need the scaling. V. -Original Message- From: [EMAIL

RE: [R] how to draw a 45 degree line on qqnorm() plot?

2005-04-03 Thread Bill.Venables
Remember this is just a diagnostic procedure and all you are really looking for is whether the normal scores plot is pretty straight. The reason for anchoring the guiding line at the quartiles is really the same reason that boxplots use quartiles for the central chunk. You don't want the guiding

RE: [R] two methods for regression, two different results

2005-04-05 Thread Bill.Venables
This is possible if x and z are orthogonal, but in general it doesn't work as you have noted. (If it did work it would almost amount to a way of inverting geenral square matrices by working one row at a time, no going back...) It is possible to fit a bivariate regression using simple linear

RE: [R] axis colors in pairs plot

2005-04-07 Thread Bill.Venables
Hi Anne, Here's one suggestion, use a simple panel function: cols - c(red, green3, blue) with(iris, pairs(iris[, -5], main = Andersons Iris Data - 3 species, panel = function(x, y, ...) points(x, y, pch = (2:4)[Species], col = cols[Species], ...) )) Bill Venables

RE: [R] Re: beta distribution in terms of it's mean and standarddeviation

2005-04-10 Thread Bill.Venables
For three of the beta distribution functions in R the parameters defining the distribution are alpha, beta and 'ncp'. Pretty trivially, there is no bijection between these three and the mean and variance, but for the special case of ncp = 0, I think there is. Rather than just write it down, it's

RE: [R] plotting Principal components vs individual variables.

2005-04-10 Thread Bill.Venables
At the cost of breaking the thread I'm going to change your subject and replace 'Principle' by 'Principal'. I just can't stand it any longer... OK, here is how I would solve your other problems. First put wh - c(USA, New Zealand, Dominican Republic, Western Samoa, Cook Islands)

RE: [R] glm family=binomial logistic sigmoid curve problem

2005-04-11 Thread Bill.Venables
Couple of points: * If you provide relative frequencies for the binomial response, you need also to give weights so that the actual counts can be reconstructed. This is what the warning message is telling you: if you reconstruct the counts using the default (unity) weights, the counts are not

Re: [R] D(dnorm...)?

2006-01-25 Thread Bill.Venables
Hi Spencer, I think if you have a problem that needs a lot of symbolic manipulation you are probably better off driving it directly from something like Maple or Mathematica (I prefer maple, actually) than trying to drive it from R. It just gets too clumsy. On the other hand it is very handy

Re: [R] D(dnorm...)?

2006-01-25 Thread Bill.Venables
While symbolic computation is handy, I actually think a more pressing addition to R is some kind of automatic differentiation facility, particularly 'reverse mode' AD, which can be spectacular. There are free tools available for it as well, though I don't know how well developed they are. See:

Re: [R] How do you convert this from S Plus to R - any help appreciated . thanks

2006-01-27 Thread Bill.Venables
This particular call to exportData is probably equivalent in effect to the R call: write.table(MU.Cost, file = paste(C:/RAUDSL/S, as.character(MU.Cost$Run.Id[1]), .,as.character(MU.Cost$MU.Id[1]),

Re: [R] Creating 3D Gaussian Plot

2006-01-28 Thread Bill.Venables
Getting a picture like this is pretty easy. e.g. x - y - seq(-5, 5, len = 200) X - expand.grid(x = x, y = y) X - transform(X, z = dnorm(x, -2.5)*dnorm(y) - dnorm(x, 2.5)*dnorm(y)) z - matrix(X$z, nrow = 200) persp(x, y, z, col = lightgoldenrod, border = NA, theta = 30, phi = 15, ticktype =

RE: [R] factors in multinom function (nnet)

2005-04-12 Thread Bill.Venables
Alexandre, I have a couple of remarks to make, not all of which you might find immediately helpful, I regret to say. * The choice between using predictors linearly or in factor versions is a modelling choice that is in no way specific to multinom. It is a general aspect of modelling that has to

RE: [R] Getting subsets of a data frame

2005-04-15 Thread Bill.Venables
You should look at ?[ and look very carefully at the drop argument. For your example sw[, 1] is the first component of the data frame, but sw[, 1, drop = FALSE] is a data frame consisting of just the first component, as mathematically fastidious people would expect. This is a

RE: [R] String in data frame

2005-04-15 Thread Bill.Venables
str - as.character(d$name) should do the trick. (damn... my shift key just broke as well...) bill venables. -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Cuichang Zhao Sent: Saturday, 16 April 2005 2:00 PM To: r-help@stat.math.ethz.ch Subject: [R]

RE: [R] chronological ordering of factor in lm() and plot()

2005-04-15 Thread Bill.Venables
First put day.names - c(sun, mon, tue, wed, thu, fri, sat) then days - factor(as.character(days), levels = day.names) will ensure the ordering you want. Bill Venables. -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Eric C. Jennings Sent: Saturday,

RE: [R] nls segmented model with unknown joint points

2005-04-16 Thread Bill.Venables
This is how I'd write the formula for use with nls/nlme: y ~ b41*(x - 1) + b42*(x^2 - 1) + ifelse((a41 - x) = 0, b43*(a41 - x)^2, 0) + ifelse((a42 - x) = 0, b44*(a42 - x)^2, 0) This is a direct translation from your funny foreign-looking code below that probably makes it clear what's going

RE: [R] array indexing and which

2005-04-17 Thread Bill.Venables
You need to think about it just a bit harder. [Hint: what happens if you leave out the first 'which' and just make ids - (d[, 1] 0) does it work then...?] -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Werner Wernersen Sent: Monday, 18 April 2005

RE: [R] generalized linear mixed models - how to compare?

2005-04-19 Thread Bill.Venables
Andrew Criswell asks: Hello All: Should I conclude from this discussion that there is no practical means by which nested generalized mixed models can be compared from output produced through glmmPQL or GLMM? [WNV] The picture is, in my view, not as bleak as

RE: [R] Using R to illustrate the Central Limit Theorem

2005-04-21 Thread Bill.Venables
Here's a bit of a refinement on Ted's first suggestion. N - 1 graphics.off() par(mfrow = c(1,2), pty = s) for(k in 1:20) { m - (rowMeans(matrix(runif(M*k), N, k)) - 0.5)*sqrt(12*k) hist(m, breaks = FD, xlim = c(-4,4), main = k, prob = TRUE, ylim = c(0,0.5), col =

RE: [R] question about about the drop1

2005-04-23 Thread Bill.Venables
Ronggui asks: : -Original Message- : From: [EMAIL PROTECTED] : [mailto:[EMAIL PROTECTED] On Behalf Of ronggui : Sent: Saturday, 23 April 2005 5:41 PM : To: r help : Subject: [R] question about about the drop1 : : : the data is : : table.8.3-data.frame(expand.grid( :

RE: [R] Anova - interpretation of the interaction term

2005-04-22 Thread Bill.Venables
: -Original Message- : From: [EMAIL PROTECTED] : [mailto:[EMAIL PROTECTED] On Behalf Of : michael watson (IAH-C) : Sent: Friday, 22 April 2005 7:47 PM : To: r-help@stat.math.ethz.ch : Subject: [R] Anova - interpretation of the interaction term : : : Hi : : So carrying on my use of

RE: [R] A question on the library lme4

2005-04-23 Thread Bill.Venables
Luis Fernando Chaves asks: : -Original Message- : From: [EMAIL PROTECTED] : [mailto:[EMAIL PROTECTED] On Behalf Of Luis : Fernando Chaves : Sent: Sunday, 24 April 2005 11:29 AM : To: [EMAIL PROTECTED] : Subject: [R] A question on the library lme4 : : : Hi, : : I ran the following

RE: [R] The eigen function

2005-04-25 Thread Bill.Venables
To me this is not at all surprising. If you read the help info for eigen it says clearly that calculating the eigenvectors is the slow part. So it is entirely likely that completely different algorithms will be used if you are asking for only the eigenvalues, or if you are asking for both

RE: [R] How to extract function arguments literally

2005-04-29 Thread Bill.Venables
instead of as.character(substitute(arg)) use deparse(substitute(arg)) : -Original Message- : From: [EMAIL PROTECTED] : [mailto:[EMAIL PROTECTED] On Behalf Of Shigeru Mase : Sent: Saturday, 30 April 2005 1:24 PM : To: r-help@stat.math.ethz.ch : Subject: [R] How to extract function

RE: [R] Roots of quadratic system.

2005-05-01 Thread Bill.Venables
Are you looking for a unique solution or families of solutions? Can't you turn a root-finding problem for a system of equations with a unique solution into an optimisation problem, anyway? E.g. You want to solve f1(x) = g1 f2(x) = g2 ... Why not optimise L(x) = (f1(x) - g1)^2 + (f2(x) -

RE: [R] Recursive partitioning with multicollinear variables

2004-02-09 Thread Bill.Venables
No, for regression trees collinearity is a non-issue, because it is not a linear procedure. Having variables that are linearly dependent (even exactly so) merely widens the scope of choice that the algorithm has to make cuts. I'm not sure what you mean by Multicollinear variables should appear

RE: [R] profile error on an nls object

2004-03-18 Thread Bill.Venables
Adrian Dragulescu asks: Hello all, This is the error message that I get. hyp.res - nls(log(y)~log(pdf.hyperb(theta,X)), data=dataModel, + start=list(theta=thetaE0), + trace=TRUE) 45.54325 : 0.100 1.3862944 -4.5577142 0.0005503 3.728302 :

RE: [R] binding vectors or matrix using their names

2004-03-24 Thread Bill.Venables
Goodness Patrick, this must surely qualify for the obfuscated R competition finals. I love it! There are two solutions I can think of with do.call and here they are: x - 1 x2 - runif(10) x12 - c(x, x2) do.call(cbind, lapply(x12, as.name)) x x2 [1,] 1 0.99327265 [2,] 1

RE: [R] Can't seem to finish a randomForest.... Just goes and goes!

2004-04-05 Thread Bill.Venables
Alternatively, if you can arrive at a sensible ordering of the levels you can declare them ordered factors and make the computation feasible once again. Bill Venables. -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Torsten Hothorn Sent: Monday, 5 April

Re: [R] reduce levels

2005-11-07 Thread Bill.Venables
sub$mm - factor(sub$mm) is the simplest way to change a single factor in this way. To do a whole data frame you just need a loop: drop_unused_levels - function(data) as.data.frame(lapply(data, function(x) if(is.factor(x)) factor(x) else x )) Here's your example again, but witn a

Re: [R] problems with glm

2006-01-15 Thread Bill.Venables
used):+61 4 1963 4642 Home Phone: +61 7 3286 7700 mailto:[EMAIL PROTECTED] http://www.cmis.csiro.au/bill.venables/ -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Roland R Regoes Sent: Sunday, 15 January 2006 11

Re: [R] Making a markov transition matrix

2006-01-21 Thread Bill.Venables
AUSTRALIA Office Phone (email preferred): +61 7 3826 7251 Fax (if absolutely necessary):+61 7 3826 7304 Mobile (rarely used):+61 4 1963 4642 Home Phone: +61 7 3286 7700 mailto:[EMAIL PROTECTED] http://www.cmis.csiro.au/bill.venables/ -Original

Re: [R] Making a markov transition matrix

2006-01-22 Thread Bill.Venables
That solution for the case 'with gaps' merely omits transitions where the transition information is not for a single time step. (Mine can be modified for this as well - see below.) But if you know that a firm went from state i in year y to state j in year y+3, say, without knowing the

Re: [R] D(dnorm...)?

2006-01-25 Thread Bill.Venables
Yes Bert, this time you are missing something (unusually) ... As Brian Ripley pointed out 'dnorm' is in the derivative table, *but* only as a function of one variable. So if you want to find the derivative of dnorm(x, mean, sigma) you have to write it as 1/sigma * dnorm((x - mu)/sigma). Here

Re: [R] Command Line Prompt Symbol

2006-11-09 Thread Bill.Venables
://www.cmis.csiro.au/bill.venables/ -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Jacob van Wyk Sent: Friday, 10 November 2006 3:33 PM To: r-help@stat.math.ethz.ch Subject: [R] Command Line Prompt Symbol Hi I run R in Windows. Is there a simple way of changing

Re: [R] Force square crosstabulation

2006-12-02 Thread Bill.Venables
Use factors with specified levels. lev - letters[1:4] table(factor(letters[1:4], levels = lev), factor(letters[c(1:3,3)], levels = lev)) a b c d a 1 0 0 0 b 0 1 0 0 c 0 0 1 0 d 0 0 1 0 -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On

Re: [R] strings as factors

2006-12-11 Thread Bill.Venables
Here is a possibility: test - expand.grid(id = 1:2, sex = c('male', 'female')) sapply(test, class) id sex integer factor test - transform(test, sex = as.character(sex)) sapply(test, class) id sex integer character But I am surprised at the reason you

Re: [R] How to sum one column in a data frame keyed on other columns

2006-12-12 Thread Bill.Venables
Here is an elementary way of doing it: dat url time somethingirrelevant visits 1 www.foo.com 1:00 xxx100 2 www.foo.com 1:00 yyy 50 3 www.foo.com 2:00 xyz 25 4 www.bar.com 1:00 xxx200 5 www.bar.com 1:00

Re: [R] Higher Dimensional Matrices

2006-12-25 Thread Bill.Venables
Lars from space [sic] asks: -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of downunder Sent: Monday, 25 December 2006 12:31 PM To: r-help@stat.math.ethz.ch Subject: [R] Higher Dimensional Matrices Hi all. I want to calculate partial

Re: [R] strange logical results

2006-12-29 Thread Bill.Venables
Hi Erin, You would be safe on a machine that represented floating point numbers in base 10, and I haven't seen one of those for such a long time... All modern machines use base 2 for floating point numbers. The moral of the story is not to believe what you see printed. The number you see

Re: [R] if ... problem with compound instructions

2006-12-31 Thread Bill.Venables
Mobile (rarely used):    +61 4 1963 4642 Home Phone:  +61 7 3286 7700 mailto:[EMAIL PROTECTED] http://www.cmis.csiro.au/bill.venables/   -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Richard Rowe Sent: Monday, 1 January

Re: [R] Vectorize rearrangement within each column

2007-01-19 Thread Bill.Venables
necessary):+61 7 3826 7304 Mobile (rarely used):+61 4 1963 4642 Home Phone: +61 7 3286 7700 mailto:[EMAIL PROTECTED] http://www.cmis.csiro.au/bill.venables/ -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Osorio

Re: [R] comparing two matrices

2007-01-21 Thread Bill.Venables
But this is using paste() the wrong way round. A better way would be join - function(x) do.call(paste, c(as.data.frame(x), sep = \r)) which(join(mat1) %in% join(mat2)) [1] 8 13 16 19 24 This is essentially the technique used by duplicated.data.frame Bill Venables -Original Message-

Re: [R] Need to fit a regression line using orthogonal residuals

2007-01-30 Thread Bill.Venables
Jonathon Kopecky asks: -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Jonathon Kopecky Sent: Tuesday, 30 January 2007 5:52 AM To: r-help@stat.math.ethz.ch Subject: [R] Need to fit a regression line using orthogonal residuals I'm trying to fit a simple

Re: [R] resolving expand.grid NA errors

2007-03-25 Thread Bill.Venables
:+61 7 3286 7700 mailto:[EMAIL PROTECTED] http://www.cmis.csiro.au/bill.venables/ -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Bob Green Sent: Monday, 26 March 2007 6:30 AM To: r-help@stat.math.ethz.ch Subject: [R] resolving

Re: [R] Problem dropping rows based on values in a column

2007-03-25 Thread Bill.Venables
: (I don't have one!) Home Phone:+61 7 3286 7700 mailto:[EMAIL PROTECTED] http://www.cmis.csiro.au/bill.venables/ -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of John Sorkin Sent: Monday, 26 March 2007 12:19 PM To: r-help

Re: [R] Hotelling T-Squared vs Two-Factor Anova

2007-04-15 Thread Bill.Venables
I take it all subjects are measured at the same time points, or Hotelling's T^2 becomes rather messy. The essential difference lies in the way the variance matrix is modelled. The usual repeated measures model would model the variance matrix as equal variances and equal covariances, i.e. with

Re: [R] Simple question about function with glm

2007-05-06 Thread Bill.Venables
There is a statistical problem and a code problem. The statistical problem is that if your 'x' has a mean that depends non-trivially on predictors, then you would not expect its distribution ignoring predictors to be normal. You would expect the residuals after modelling to be normal. Basically

Re: [R] number of days

2007-05-14 Thread Bill.Venables
AUSTRALIA Office Phone (email preferred): +61 7 3826 7251 Fax (if absolutely necessary):+61 7 3826 7304 Mobile:(I don't have one!) Home Phone: +61 7 3286 7700 mailto:[EMAIL PROTECTED] http://www.cmis.csiro.au/bill.venables/ -Original Message

Re: [R] converting a row of a data.frame to a vector

2007-05-15 Thread Bill.Venables
3826 7304 Mobile: (I don't have one!) Home Phone:+61 7 3286 7700 mailto:[EMAIL PROTECTED] http://www.cmis.csiro.au/bill.venables/ -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Andrew Yee Sent

Re: [R] name of object in quotes

2007-05-23 Thread Bill.Venables
: (I don't have one!) Home Phone:+61 7 3286 7700 mailto:[EMAIL PROTECTED] http://www.cmis.csiro.au/bill.venables/ -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Gonzalo Rivero Sent: Wednesday, 23 May 2007 8:14

Re: [R] Speeding up resampling of rows from a large matrix

2007-05-25 Thread Bill.Venables
, Cleveland, 4163 AUSTRALIA Office Phone (email preferred): +61 7 3826 7251 Fax (if absolutely necessary): +61 7 3826 7304 Mobile:(I don't have one!) Home Phone: +61 7 3286 7700 mailto:[EMAIL PROTECTED] http://www.cmis.csiro.au/bill.venables/ -Original

Re: [R] linear model by month

2007-05-28 Thread Bill.Venables
, 4163 AUSTRALIA Office Phone (email preferred): +61 7 3826 7251 Fax (if absolutely necessary): +61 7 3826 7304 Mobile:(I don't have one!) Home Phone: +61 7 3286 7700 mailto:[EMAIL PROTECTED] http://www.cmis.csiro.au/bill.venables/ -Original Message- From

Re: [R] looking for the na.omit equivalent for a matrix of characters

2007-05-28 Thread Bill.Venables
7251 Fax (if absolutely necessary): +61 7 3826 7304 Mobile:(I don't have one!) Home Phone: +61 7 3286 7700 mailto:[EMAIL PROTECTED] http://www.cmis.csiro.au/bill.venables/ -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf

Re: [R] Factor function: odd behavior when labels argument containsduplicates?

2007-05-30 Thread Bill.Venables
Laboratories PO Box 120, Cleveland, 4163 AUSTRALIA Office Phone (email preferred): +61 7 3826 7251 Fax (if absolutely necessary): +61 7 3826 7304 Mobile:(I don't have one!) Home Phone: +61 7 3286 7700 mailto:[EMAIL PROTECTED] http://www.cmis.csiro.au/bill.venables

Re: [R] AIC consistency with S-PLUS

2007-05-31 Thread Bill.Venables
don't have one!) Home Phone: +61 7 3286 7700 mailto:[EMAIL PROTECTED] http://www.cmis.csiro.au/bill.venables/ -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Alice Shelly Sent: Friday, 1 June 2007 10:07 AM To: r-help@stat.math.ethz.ch

Re: [R] scan a directory and then make a string vector consisting offile names

2007-05-31 Thread Bill.Venables
: +61 7 3286 7700 mailto:[EMAIL PROTECTED] http://www.cmis.csiro.au/bill.venables/ -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Taka Matzmoto Sent: Friday, 1 June 2007 12:19 PM To: r-help@stat.math.ethz.ch Subject: [R] scan a directory

Re: [R] Retain names in conversion of matrix to vector

2007-06-14 Thread Bill.Venables
Box 120, Cleveland, 4163 AUSTRALIA Office Phone (email preferred): +61 7 3826 7251 Fax (if absolutely necessary): +61 7 3826 7304 Mobile:(I don't have one!) Home Phone: +61 7 3286 7700 mailto:[EMAIL PROTECTED] http://www.cmis.csiro.au/bill.venables

Re: [R] correlation comparison one more time

2007-06-17 Thread Bill.Venables
): +61 7 3826 7304 Mobile: (I don't have one!) Home Phone: +61 7 3286 7700 mailto:[EMAIL PROTECTED] http://www.cmis.csiro.au/bill.venables/ -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of rafael

Re: [R] Subscripting specified variables in a function

2007-06-26 Thread Bill.Venables
(if absolutely necessary): +61 7 3826 7304 Mobile: +61 4 8819 4402 Home Phone: +61 7 3286 7700 mailto:[EMAIL PROTECTED] http://www.cmis.csiro.au/bill.venables/ -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Zodet, Marc

[R] termplot with uniform y-limits

2007-07-02 Thread Bill.Venables
Office Phone (email preferred): +61 7 3826 7251 Fax (if absolutely necessary): +61 7 3826 7304 Mobile: +61 4 8819 4402 Home Phone: +61 7 3286 7700 mailto:[EMAIL PROTECTED] http://www.cmis.csiro.au/bill.venables

Re: [R] Question about PCA with prcomp

2007-07-02 Thread Bill.Venables
...but with 500 variables and only 20 'entities' (observations) you will have 481 PCs with dead zero eigenvalues. How small is 'smaller' and how many is a few? Everyone who has responded to this seems to accept the idea that PCA is the way to go here, but that is not clear to me at all. There

Re: [R] How to calculate the index the number of speciescombinations?

2007-07-07 Thread Bill.Venables
Here is a step by step explanation. The way you present the data is as species (rows) by sites (columns) data frame dim(species_x_sites) [1] 17 20 There are in fact only 19 sites as one of the columns of the data frame is the species name: names(species_x_sites) [1] Species Cuba

Re: [R] a little problem on selecting a subset from dataset A accordingto dataset B?

2007-07-09 Thread Bill.Venables
AB - with(B, subset(A, coords.x1 %in% X1)) AB coords.x1 coords.x2 0 542250.9 3392404 7 541512.5 3394722 8 541479.3 3394878 9 538903.4 3395943 18 543274.0 3389919 19 543840.8 3392012 -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On

Re: [R] Within matrix

2007-07-09 Thread Bill.Venables
mailto:[EMAIL PROTECTED] http://www.cmis.csiro.au/bill.venables/ -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of [EMAIL PROTECTED] Sent: Tuesday, 10 July 2007 9:25 AM To: r-help@stat.math.ethz.ch Subject: [R] Within matrix Hi all, I am working on cluster, I

Re: [R] type III ANOVA for a nested linear model

2007-07-10 Thread Bill.Venables
The message from this cute little data set is very clear. Consider fm - aov(resp ~ A*B + A/C, mydata) drop1(fm, test = F) Single term deletions Model: resp ~ A * B + A/C Df Sum of Sq RSS AIC F value Pr(F) none 65.540 47.261 A:B 216.132

Re: [R] automatically generating and accessing data frames of varyingdimensions

2007-07-12 Thread Bill.Venables
): +61 7 3826 7251 Fax (if absolutely necessary): +61 7 3826 7304 Mobile: +61 4 8819 4402 Home Phone: +61 7 3286 7700 mailto:[EMAIL PROTECTED] http://www.cmis.csiro.au/bill.venables/ -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL

Re: [R] t-distribution

2007-08-01 Thread Bill.Venables
for the upper tail: 1-pt(1.11, 9) [1] 0.1478873 -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Nair, Murlidharan T Sent: Thursday, 2 August 2007 4:43 AM To: r-help@stat.math.ethz.ch Subject: [R] t-distribution If I have a calculated t can I get the

Re: [R] t-distribution

2007-08-01 Thread Bill.Venables
: +61 7 3286 7700 mailto:[EMAIL PROTECTED] http://www.cmis.csiro.au/bill.venables/ -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Ben Bolker Sent: Thursday, 2 August 2007 4:57 AM To: r-help@stat.math.ethz.ch Subject: Re: [R] t-distribution Bill.Venables

Re: [R] length of a string

2007-09-05 Thread Bill.Venables
: +61 7 3286 7700 mailto:[EMAIL PROTECTED] http://www.cmis.csiro.au/bill.venables/ -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of João Fadista Sent: Wednesday, 5 September 2007 11:51 PM To: r-help@stat.math.ethz.ch Subject: [R] length of a string