Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | Andrea Rispoli <andrea.rspl@gmail.com> |
To | statalist@hsphsun2.harvard.edu |
Subject | Re: st: random sampling matching the characteristics of the sample |
Date | Thu, 3 May 2012 11:01:24 +0100 |
Thank you all very much for getting back to me! Unfortunately the rev does not provide much details. Based on your suggestions, I have now identified the command pscore and psmatch2 to use propensity scores. A brief follow up question: when I use pscore, I end up with a certain number of blocks, satosfying the balancing property. If I understood correctly the intuition behind this method, I shall select now some blocks of firms where the distribution of x is more balanced and that have high pscore and see whether my analysis hold in those groups. Is this correct? Or is there another method to chose the blocks to use? Thank you again! On Tue, May 1, 2012 at 2:54 PM, David Hoaglin <dchoaglin@gmail.com> wrote: > Dear Andrea, > > Did the reviewer explain the reason for wanting a sample of the x=0 > observations that is comparable in size to the x=1 observations? As > others have commented, you would mainly sacrifice precision, so that > looks like a mistake. It is not unheard of for a reviewer to have a > misunderstanding. The consensus is that you should not subsample. > > Samples that are "representative" of the x=0 data and the x=1 data may > well not match on age and size. Those differences are part of what > your regression model is adjusting for. You should consider whether > the coefficients of age and size are similar in the x=0 data and the > x=1 data (e.g., by fitting a model that allows separate coefficients > in the two subgroups --- that is, an interaction between x and age and > an interaction between x and size). Might that be what the reviewer > is actually concerned about? > > David Hoaglin > > On Tue, May 1, 2012 at 4:22 AM, Andrea Rispoli <andrea.rspl@gmail.com> wrote: >> Dear Stan, >> Thank you. This is the request of a reviewer. Would you recommend that >> I simply chose a random sample? > * > * 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/