[R] lme() vs aov(y ~ A*B + Error(aa %in% A + bb %in% B)) -- questions

[Martin Maechler]

Here is a reproducible (when you're on-net) script for a
relatively simple real data (consulting) situation here.

The data analyst tried to use lme() rather than  aov( + Error()) 
and asked several questions that I couldn't easily answer and
thought to be interesting for a more general audience in any
case.

I attach the script as text/plain file that you should run
"everywhere".  The three questions are summarized at the
beginning of the file.

Martin Maechler <maechler at stat.math.ethz.ch>	http://stat.ethz.ch/~maechler/
Seminar fuer Statistik, ETH-Zentrum  LEO C16	Leonhardstr. 27
ETH (Federal Inst. Technology)	8092 Zurich	SWITZERLAND
phone: x-41-1-632-3408		fax: ...-1228			<><



-------------- next part --------------
An embedded and charset-unspecified text was scrubbed...
Name: lme-ex4.R
Url: https://stat.ethz.ch/pipermail/r-help/attachments/20030515/c43b2bd1/lme-ex4.pl