Saturday, March 11, 2006

Re: st: easy way to save regressor variable names?

1) you try looking at the saved matrices like e(b) and e(V) and get their column names (local regressors : mat colnames e(b), if that does not work, save e(b) to a temporary matrix first)

2) you should run your models as

cap noi logit whatever local myrc = _rc post topost (`myrc') (_b[]) ... (_b[]) // in generic form if `myrc' { continue, break }

just in case there is extra work on the estimation results. Posting _b[] should be safe, but you may consider posting missing values instead.

3) of course you are aware of the detrimental consequences of multiple testing and will be applying a Bonferroni correction or FDR (false discovery rates) to your p-values.

On 3/11/06, Toby Andrew <> wrote: > Dear all, > > I have 2 questions related to saving summary stats from regression > analyses: > > 1) Is there a generic way to access the list of variable names used > in a regression such as regress, mlogit & ologit? > The reason i ask is because i am performing many regressions by > looping over variables & the list of recorded variables i save > will differ from the *actual* list retained in the analysis if there > is collinearity (or i wish to use stepwise sw). > > 2) is there an "_rc" error message (or equivalent) i can record in > the summary postfile results, if the model fails to converge? > > Thanks very much, > > Toby > > * > * For searches and help try: > * > * > * >

-- Stas Kolenikov

* * For searches and help try: * * *


Links to this post:

Create a Link

<< Home

This page is powered by Blogger. Isn't yours?