similar to: Macros and functions

Typing in statements from the command line transfers to the computer a macro that was perhaps in the user's head. Putting together small sequences of carefully thought out code, in which key components have been carefully thought out and tested, has to be, for most of us, better than trying to make it all up on the run. An exception is necessary for those unusual people who who (akin to the

The following is from version 1.6.2 of R under Windows, or 1.6.1 under Mac OSX/X11 > density(1) Error in if (!(lo <- min(hi, IQR(x)/1.34))) (lo <- hi) || (lo <- abs(x[1])) || : missing value where logical needed I am not sure how this should be handled. I encountered it in connection with densityplot(). In that connection, it might be enough to modify density() so that it

You've omitted a comma. races2000 is a data frame, which for purposes of extracting rows behaves like a 2-dimenional object. The following works fine: hills2000 <- races2000[races2000$type == 'hill', ] Additionally, you might like to ponder > type <- races2000[names(races2000)=="type"] > type[1:4] Error in "[.data.frame"(type, 1:4) :

expression() accepts multiple expressions as arguments, thus: plot(1:2, 1:2) legend("topleft", expression(y == a * x^b, "where "* paste(y=="wood; ", x=="dbh"))) Is there a way to do this when values are to be substituted for a and b? i.e., the first element of the legend argument to legend() becomes,

I am puzzled by the warning message in the output below. It appears whether or not I fit the seasonal term (but the precise point of doing this was to fit what is effectively a second seasonal term). Is there some deep reason why AR parameters ("Warning message: some AR parameters were fixed: ...") should somehow intrude into the fitting of a model that has only MA terms? >

I have posted, at http://wwwmaths.anu.edu.au/~john/r/newsets/ image (.rda) files, and first stabs at .Rd files for various data on deaths in London from 1629 to 1939. (There are of course gaps.) The sources (Guy 1882 & Stocks 1942) are documented in the .Rd files: (1) poxetc: measles, smallpox & total deaths: 1629-1881 [I have deliberately left several inconsistencies that were in

Consider the following analysis of a class experiment done as a Latin Square: > spinner <- gl(4,4,16,label=c("Murray","Angela","Shasha","Stephen")) > order <- gl(4,1,16) > treat <- scan() 1: 1 2 4 3 5: 4 3 1 2 9: 3 4 2 1 13: 2 1 3 4 17: Read 16 items > coin <-

With lme4, use of mcmcsamp can be insightful. (Douglas Bates drew my attention to this function in a private exchange of emails.) The distributions of random effects are simulated on a log scale, where the distributions are much closer to symmetry than on the scale of the random effects themselves. As far as I can see, this is a straightforward use of MCMC to estimate model parameters; it is not

Under help(matrix) it is written: 'is.matrix' tests if its argument is a (strict) matrix. It is generic: you can write methods to handle specific classes of objects, see InternalMethods. Further down, under "Details", the meaning of "strict" is explained more explicitly: 'is.matrix' returns 'TRUE' if 'x' is a matrix

You need to give the model formula that gave your output. There are two sources of variation (at least), within and between locations; though it looks as though your analysis may have tried to account for this (but if so, the terms are not laid out in a way that makes for ready interpretation. The design is such (two locations) that you do not have much of a check that effects are consistent over

I'd like to make the following change to termplot(): Add panel=points as an extra parameter. Replace if (partial.resid) points(xx, pres[, i], cex = cex, pch = pch, col = col.res, ...) by if (partial.resid) panel(xx, pres[, i], cex = cex, pch = pch, col = col.res, ...) Also, I think, add col.smooth, span and iter as named parameters; see below.

The following works fine with the x11 device, though it may well be that an initial plot is overwritten. With a pdf or postscript device, I get two plots, the first of which still has the red border from having the focus, while the second is the plot that I want. library(lattice); library(grid) plt <- xyplot(uptake ~ conc, groups=Plant, data=CO2) print(plt)

Although base graphics does not mix with lattice in the one graph, I've found that print.trellis(position=..., ) and the use of par(fig=...) to put regular and trellis graphics on the one graphics page works like a treat, at least in version 2.0.1 of R. [Base graphics functions that are themselves inconsistent with par(fig=...) are obviously disallowed.] I am wondering whether there are

<soap-box> While I agree with John about abuse of methodology, I can't subscribe to the "failure to read the manual" proposition. I don't mean to lecture, but it would seem to me that people who, like me, will probably gain far more from this list than we will be able to contribute (at least in the near term) owe it to those who will likely contribute far more than they

Is there any way, after use of print.trellis(), to obtain the co-ordinates of the plot region, e.g., in what are then the native co-ordinates? e.g. library(DAAG) library(lattice); library(grid) data(cuckoos) pushViewport(viewport(layout=grid.layout(2, 1))) pushViewport(viewport(layout.pos.row=1)) cuckoos.strip <- stripplot(species ~ length, data=cuckoos) print(cuckoos.strip,

There are answers that could and should be applied in specific situations. At least in academia and in substantial research teams, statisticians ought to have a prominent part in many of the research teams. Senior statisticians should have a prominent role in deciding the teams to which this applies. why should it be ok to do combine high levels of chemical expertise with truly appalling

Fisher is not the only person that it may be necessary to read 4 or 5 times. The same may be the case for side comments that Bill Venables is wont to make. Now to the parallel universe that I have in mind. I wonder whether the time is opportune for a list that focuses on "Statistical Methodology for R Users". The difference from other statistical methodology lists is that it will be

This message is aimed at anyone who may be using exercises from my book with John Braun for teaching purposes. I am using this channel of communication in the absence of any other obvious effective channel. I ask the forbearance of list members. Our intention is to post solutions to selected exercises (the more challenging exercises) on the web, via a link from

In co-operation with Markus Hegland and myself, Zhongwen Ding has written a package, based partly on Markus Hegland's code, that provides a parallel processing interface to a remote multi-processsor system. Pyro (Python Remote Objects) and R must both be installed, both on the client machine and on the remote server. The system uses rsync, with an ssh protocol, to handle file transfer. Once

Peter Dalgaard writes: > Bill.Venables at cmis.csiro.au writes: > ........ > > [WNV] Now there's an insight! In fact I think that once you get used to > > the style you get to appreciate it. The commercial world substitutes > > politeness for candour. True candour can be disconcerting but it does get > > the message across much quicker. > Also, this