From: Colin Beale <c.beale_at_macaulay.ac.uk>

Date: Fri 26 Jan 2007 - 09:58:33 GMT

Date: Fri 26 Jan 2007 - 09:58:33 GMT

lmerWrapper <- function(formula, data, family = gaussian, method = c("REML",

xNew <- runif(0,1, length(data[,1])) fNew <- sample(1:4, length(data[,1]), replace = T) data <- as.data.frame(cbind(data, xNew, fNew))formula <- update(formula, .~. + xNew + (1|fNew)) out <- lmer (formula = formula, data = data, family = family, method =

method, weights = weights, control = control, start = start, subset = subset, na.action = na.action, offset = offset, contrasts = contrasts, model = model)}

dat <- data.frame(Y = rnorm(100), X1 = rnorm(100), X2 = rnorm(100),

F1 = as.factor(sample(1:4, 400, replace = T))) test <- lmerWrapper (Y ~ X1 + X2 + (1|F1), data = dat)

This function attempts to create two new variables, add these to the data.frame and modify the formula for include these two new variables, and then fit this expanded model using lmer. Clearly the example is silly, but it illustrates the problem as it fails with the error:

Error in eval(expr, envir, enclos) : object "xNew" not found

because a function within lmer (lmerFrames) makes an eval call where
the environment is specified as the .GlobalEnv which doesn't contain
xNew - it needs to be looking in the environment from which it was
called rather than going right back to the root. In a more general
context, I might like to create a function where I don't specify a new
data.frame in the wrapper, but want the function to search the back
down

the search path for each component, finding xNew in the environment of
the wrapper function and X1 in the .GlobalEnv. Is there a general
solution to this? Or do I need to create a modified lmer function that
calls a modified lmerFrames function where I specify the environment
differently? There's quite a lot in the archives dealing with
environments and search paths, but I'm either not understanding how to
apply the wisdom therein, or not finding the specific answer to my
problem, and I should say that I have this problem with more than just
the lmer function.

Thanks for any pointers,

Colin

> sessionInfo()

R version 2.4.1 (2006-12-18)

i386-pc-mingw32

locale:

LC_COLLATE=English_United Kingdom.1252;LC_CTYPE=English_United
Kingdom.1252;LC_MONETARY=English_United

Kingdom.1252;LC_NUMERIC=C;LC_TIME=English_United Kingdom.1252

attached base packages:

[1] "stats" "graphics" "grDevices" "datasets" "tcltk"
"utils"

"methods" "base"

other attached packages:

debug mvbutils lme4 Matrix lattice svSocket

svIO R2HTML svMisc svIDE "1.1.0" "1.1.1" "0.9975-10" "0.9975-8" "0.14-16" "0.9-5" "0.9-5" "1.58" "0.9-5" "0.9-5"

Dr. Colin Beale

Spatial Ecologist

The Macaulay Institute

Craigiebuckler

Aberdeen

AB15 8QH

UK

Tel: 01224 498245 ext. 2427

Fax: 01224 311556

Email: c.beale@macaulay.ac.uk

-- Please note that the views expressed in this e-mail are those of the sender and do not necessarily represent the views of the Macaulay Institute. This email and any attachments are confidential and are intended solely for the use of the recipient(s) to whom they are addressed. If you are not the intended recipient, you should not read, copy, disclose or rely on any information contained in this e-mail, and we would ask you to contact the sender immediately and delete the email from your system. Thank you. Macaulay Institute and Associated Companies, Macaulay Drive, Craigiebuckler, Aberdeen, AB15 8QH. ______________________________________________ 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.Received on Fri Jan 26 21:05:07 2007

Archive maintained by Robert King, hosted by
the discipline of
statistics at the
University of Newcastle,
Australia.

Archive generated by hypermail 2.1.8, at Fri 26 Jan 2007 - 13:30:30 GMT.

*
Mailing list information is available at https://stat.ethz.ch/mailman/listinfo/r-help.
Please read the posting
guide before posting to the list.
*