re: st: permutation, strata() for empirical statistic distributions

[David Airey <david.airey@vanderbilt.edu>]

Here's a concrete example of what I want to do using permute. I have a 
simple data set with 2 groups, 5 subjects per group, and 10 replicate 
measures per subject. The anova statement for this data is:

. anova y group / subject|group /

I'd like to use permute in the same way as the example on page 157 of 
R[N-R], "permute", to get a distribution of statistics for my data 
permuted within subject within group. Does "permute" handle nested 
models? I'm assuming the option strata(subject group) does this?

How would one write a program equivalent to the one given on page 157 
for the model above? The program on page 157 for the anova model "anova 
y treatment subject" is:

program panova
	version 8.0
	args response fac_intrst fac_other
	anova `response' `fac_intrst' `fac_other'
	test `fac_intrst'
end

This program is called by the permute statement:

. permute treatment "panova y treatment subject" treatmentF=r(F) 
modelF=e(F), reps(1000) strata(subject) saving(permanova)

My problem is that the examples don't tell me what to do with the / | 
characters in my anova statement.

Thanks,

Dave







*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/