Jeannette Wicks-Lim wrote:
I'm used to working with very large data sets in my regression analyses, but
I've encountered a situation where my N is 24, and my k (number of
independent vars) is 9. I may be able to expand the sample to N=36, but in
any case, how do you decide when a sample is "too" small to be useful? Does
it just depend on your results (e.g., standard errors are really large)?
-------------------------------------------------------------------------------
There are several rules of thumb floating around for sample size in multiple
regression. You can find one at
www2.chass.ncsu.edu/garson/pa765/regress.htm#samplesize
Joseph Coveney
*
* 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/
