Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: Computing effect size for a clustered randomized control trial


From   Michael Norman Mitchell <Michael.Norman.Mitchell@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Computing effect size for a clustered randomized control trial
Date   Mon, 03 May 2010 18:30:51 -0700

Greetings

I concur with Scott, that Optimal Design is very useful in this kind of situation. I would especially recommend taking time with the user manual for this program. The program is super well designed and easy to use, and I think it is very tempting just to use the program without the documentation. However, I feel that is cheating oneself because the manual is exceptional in the way that it explains the underlying issues and how to conceptualize them in terms of using their software. I think the trickiest bit, in your case, will be the combination of the clustering and the repeated measures. I think you will get the most mileage out of conceptualizing the "pre test" as a level 1 covariate and I believe the optimal design software will permit this. However, as the manual describes, it is "level 2" covariates that will have the biggest impact on power. If the software does not support level 1 covariates in such a model, I don't think it will alter the power estimate that much.

I hope that is useful additional information.

Michael N. Mitchell
See the Stata tidbit of the week at...
http://www.MichaelNormanMitchell.com

On 2010-05-03 6.08 PM, Scott Baldwin wrote:
I'm not aware of any built in or user-written method in Stata for
computing power in cluster randomized trials. You can try the Optimal
Design software
(http://sitemaker.umich.edu/group-based/optimal_design_software) or
the formulae in David Murray's book "Design and analysis of group
randomized trials."

Best,
Scott


On Mon, May 3, 2010 at 5:23 PM, Joe McCrary<joe.mccrary@gmail.com>  wrote:
I am designing a randomized control trial, where we are going to
select about 12 students per classroom and randomize them into 3
groups, a control and 2 treatment groups. Is there a way I can compute
the number of classrooms needed for the study using the following
criteria:

Desired power=0.8
Estimated effect size = 0.2
alpha = 0.0167
1 pre-test measure
1 post-test measure
approx correlation between the two measures = 0.25

--
Joe McCrary
Senior Research Associate
WestEd-Atlanta
260 Peachtree St., Suite 2200
Atlanta, GA 30303

ph: 541-782-8626
fax: 404-393-3797

Skype: joe.mccrary
Google talk; joe.mccrary
**********************

"No problem can be solved from the same level of consciousness that created it."
--Albert Einstein
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index