Date: Tue, 11 Mar 2003 16:29:35 -0800
Sender: "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From: "David L. Cassell" <cassell.david@EPAMAIL.EPA.GOV>
Subject: Re: Power calculations for longitudinal models via simulation
Content-type: text/plain; charset=us-ascii
Simcha Pollack <spollack@WINTHROP.ORG> wrote:
> We often need to do a power analysis for a proposed clinical
> that will generate longitudinal data. The available power formulas
> programs do not allow us to include realistic models, or they require
> specification of parameters that are difficult to estimate.
> Therefore, we are trying to write a simulation that will be able to
> generate longitudinal data which corresponds to an arbitrary model.
> For example, one active population is observed for 5 periods of
> where the correlation between time points is .3 and the mean increases
> the average by 2% from one observation period to the next. The
> on placebo is similar except that the mean increases on the average by
> from observation to the next.
> After creating this data, say, 5000 times, we plan to run each
> through Proc Mixed, look how often certain parameters are significant
> thus obtain a simulation-based estimate of power.
> Are you aware of anyone who has done this? Are there books that help
> these power simulations?
I haven't seen anyone who has done this in a general fashion suitable
distribution. There are just too many possibilities to cram into one
(probably freeware) program. So I suggest you consider writing (or
someone else write) a macro to address your problem. I recommend that
consider using the concepts of my randomization-test macros for your
framework. ( http://www.wuss.org/conference/papers/DA07.pdf )
The basic idea would be as follows:
 allow enough macro parameters to control all your varying aspects:
sample sizes, number of periods, temporal correlation, average
for the differing subpopulations, other error characteristics, etc.
 use the above macro variables to fill in a data step which would
all N replicates, by replicate (so you won't even have to sort
 feed this data set into PROC MIXED, allowing more macro variables to
change the form of the model and the tests, doing the MIXED
 use ODS to snag the relevant output data set(s), and a WHERE clause
trim the data set down to the apporpriate test statistic(s)
 feed the resultant data set(s) into a null data step which does
but compute the proportion of significant results, giving you the
David Cassell, CSC
Senior computing specialist