similar to: Error() term in glm model formula

Dear R list I have an m * n matrix P and a vector V of length n containing indices for rows in P. For each of the m columns I want to extract the value in the row specified by V, and put these values into a new vector W of length n. At present I am doing this with a for.... loop, but I imagine there is a faster way that doesn?t involve loops. If anyone knows the way I would be most grateful.

Dear list, If anyone knows how to assign dimnames to matrices or arrays I would be most grateful for help. I've tried various permutations of likely-looking code but get error messages every time. I could find no example in the documentation. Many thanks, Dan Bebber Department of Plant Sciences University of Oxford South Parks Road Oxford OX1 3RB UK Tel. 01865 275000

Dear R list: I modelled changes in a variable (mconc) over time (d) for individuals (replicate) given one of three treatments (treatment) using: mconc.lme <- lme(mconc~treatment*poly(d,2), random=~poly(d,2)|replicate, data=my.data) summary(mconc.lme) shows that the linear coefficient of one of the treatments is significantly different to zero, viz. Value Std.Error

Dear List, I have circular data comprising direction and size for a number of observations. I wish to calculate statistics such as the mean direction and concentration for these data. I note that the CircStats package only deals with angular data (i.e. "Each observation is treated as a unit vector or a point on the unit circle". There appears to be no facility for weighting

Motivated by the discovery of 'loglet analysis' (http://phe.rockefeller.edu/LogletLab/) that allows one to decompose growth curves into a series of logistic equations, I attempted to do the same thing in R. SIMULATED DATA Time <- 1:200 pop.size <- SSlogis(Time,10,20,5) + SSlogis(Time,20,100,20) + rnorm(length(Time)) MY ANALYSIS results <- nls(size ~ SSlogis(Time, Asym1, xmid1,

Dear list, Apologies, I have sent this message before but received no replies so I'm trying again just in case... Motivated by the discovery of 'loglet analysis' (http://phe.rockefeller.edu/LogletLab/) that allows decomposition of growth curves into a series of logistic equations, I attempted to do the same thing in R. #SIMULATED DATA Time <- 1:200 pop.size <-

I am plotting subsets of my data, using ylim. This works fine, but the outer margin line widths of the plot are thin, due to clipping. If I include > trellis.par.set(clip=list(panel = "off")) then the outer margin line widths are fine, but the outlying data is visible. Is there any way of achieving both correct margin line widths and clipping of outlying data? Thanks, Dan Bebber

I received the following error when I attempted to update my packages: updating HTML package descriptions Warning messages: 1: DESCRIPTION file of package 'file28862' missing or broken in: packageDescription(p, lib = lib, fields = pkgFlds) 2: number of columns of result not a multiple of vector length (arg 2) in: rbind(retval, c(p, lib, desc)) 3: DESCRIPTION file of package

Dear list, there are now >400 packages available on CRAN. Would it be useful to classify these packages according to what they do (e.g. classification, graphics, spatial statistics), to assist the user in finding the appropriate package for their problem? Or perhaps the search facility is enough. I would attempt such a classification, but my knowledge of statistical methods isn't good

Could someone please give a brief explanation, or pointer to an explanation, of the following error: > arima(ts.growth, order = c(1,0,0),include.mean=T) Error in arima(ts.growth, order = c(1, 0, 0), include.mean = T) : non-stationary AR part from CSS and why it does not arise with > arima0(ts.growth, order = c(1,0,0)) Many thanks ____________________________ Dr. Daniel P. Bebber

Hello, I have a model glm(Y ~ X, family = quasipoisson(link = "identity")) I would like to vary the coefficient for X and observe the effect on the deviance. Is this possible? Many thanks, Dan Bebber Department of Plant Sciences University of Oxford

Dear list-members I am new to R and a statistics beginner. I really like the ease with which I can extract and manipulate data in R, and would like to use it primarily. I've been learning by checking analyses that have already been run in SAS. In an experiment with Y being a response variable, and group a 2-level between-subject factor, and time a 5-level within-subject factor. 2

Some notes on installing rgeos in R 2.14.0 on a Linux Mint 11 (x86_64-pc-linux-gnu) machine 1. rgeos 0.1-15 will not run with GEOS 3.2.0-1, which is the version currently available on Synaptic package manager 2. I installed GEOS 3.3.1 (the latest version) from http://trac.osgeo.org/geos/, but rgeos will not run with this either 3. I then install GEOS 3.2.3, and now rgeos works fine! It seems

glm(S ~ -1 + Mdif, family=quasipoisson(link=identity), start=strt, sdat) gives error: > Error in glm.fit(x = X, y = Y, weights = weights, start = start, etastart > = > etastart, : > cannot find valid starting values: please specify some strt is set to be the coefficient for a similar fit glm(S ~ -1 + I(Mdif + 1),... i.e. (Mdif + 1) is a vector similar to Mdif. The error

I have a data set in which I have 5000 repeated measures on 6 subjects over time (varying intervals, but measurements for all individuals are at the same times). There are two states, a "resting" state (the majority of the time), and a perturbed state. I have a continuous measurement at each time point for each of the individuals. I would like to determine the "state"

I would like to extract predicted failure times from a coxph model in library(survival). However, none of the prediction options ("lp", "risk", "expected", "terms") seem to bear any relationship to failure time. Perhaps I am asking the wrong question, but can coxph provide predicted failure times? Thanks, Dan Bebber Department of Plant Sciences University

Hello, when I try to use the filled circle (pch = 16) in a Windows metafile, it appears highly pixelated rather than as a smooth vector. The other filled circles (pch = 19 and 20) are vector circles, filled with pixels. Results are the same whether I use windows() and save or copy as a metafile, or win.metafile() Also, some of the other symbols are misshapen, e.g. the diamond pch = 23 is not

Hello, I've just located the illuminating explanation by Douglas Bates on degrees of freedom in mixed models. The take-home message appears to be: don't trust the p-values from lme. Questions: Should I give up hypothesis testing for fixed effects terms in mixed models? Has my time spent reading Pinheiro & Bates been in vain? Is there a publication on this issue? Thanks, Dan Bebber

I have obtained shapefiles for Indian states from here: http://www.maptell.com/index.php?option=com_remository&Itemid=159&func=fileinfo&filecatid=115&parent=category Problem: I want to extract centroid coordinates for each State, but there is some coding problem with the shapefiles that prevents this. #Code: #After extracting the shapefiles from the india_state.zip file, then:

Hello, I am having trouble specifying a suitable nlme model. My data structure is described by gd <- groupedData(ppath ~ lcut | exp, outer = ~ bait, inner = ~ weight, data = d) i.e. the response (ppath) of several subjects (sub) was measured at levels of a continuous variable (lcut). Subjects were given either of one level of a factor (bait), and all subjects were measured at two levels