Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | Jake <daedalus702@yahoo.com> |
To | statalist@hsphsun2.harvard.edu |
Subject | Re: st: simulation to derive power for GLM multiple regression |
Date | Tue, 9 Mar 2010 12:18:17 -0800 (PST) |
Austin, Thank you for your advice. Yes, this is a post-hoc power analysis, so the goal is to estimate power rather than estimate necessary sample size. You wrote that I could draw errors from the empirical distribution of errors in the estimated model. I wanted to make sure of something -- you said that I could sample from the estimated errors -- I assume then that I would sample *with* replacement such that each value had an equal probability of being selected? Also, since I am interested mainly in whether there is sufficient power to detect one particular effect, I would prefer to treat the parameters for the covariates as given. Would this make sense? Thank you again for you help, Jacob Felson Austin Nichols wrote: Jake <daedalus702@yahoo.com> : If you have the data on explanatory variables, you need only specify true coefs and draw error terms. This involves far fewer choice than generating all the explanatory variables, with various possible joint distributions. But you still have to make choices about what combinations of parameter values to test, and what family of distributions to draw errors from. Or you can use your estimated parameter values in the current dataset, and perhaps twice and half each, and draw errors from the empirical distribution of errors in your estimated model. If you have a negative binomial, perhaps you'd like to specify errors as being multiplicative, so y=f(X.b)e and the estimated errors are y/f(X.bhat) which you can then sample from in your simulation. Is this a post-hoc power analysis? * * 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/