R help - Dec 2008 - Power calculations where two samples are of unequal size

I have used the function power.t.test() (power calculations for one
and two sample t tests) but have noted that it handles the samples as
being the same size. How does one handle sample sizes that are
different. In other words how does one handle unbalanced designs.

Farrel Buchinsky

Hi Farrel,

I usually simulate in cases like this - pick the effect size and 
distributions you conjecture, simulate your data 10,000 times and look 
how often t.test() gets you a significant difference.

Good luck,
Stephan

Farrel Buchinsky schrieb:
> I have used the function power.t.test() (power calculations for one
> and two sample t tests) but have noted that it handles the samples as
> being the same size. How does one handle sample sizes that are
> different. In other words how does one handle unbalanced designs.
> 
> Farrel Buchinsky
> 
> ______________________________________________
> R-help at r-project.org 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.
>

On 12/9/2008 6:32 PM, Farrel Buchinsky wrote:
> I have used the function power.t.test() (power calculations for one
> and two sample t tests) but have noted that it handles the samples as
> being the same size. How does one handle sample sizes that are
> different. In other words how does one handle unbalanced designs.
library(pwr)

?pwr.t2n.test
> Farrel Buchinsky
> 
> ______________________________________________
> R-help at r-project.org 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. 
-- 
Chuck Cleland, Ph.D.
NDRI, Inc. (www.ndri.org)
71 West 23rd Street, 8th floor
New York, NY 10010
tel: (212) 845-4495 (Tu, Th)
tel: (732) 512-0171 (M, W, F)
fax: (917) 438-0894