Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: RE: RE: vselect & diff n
From
[email protected]
To
[email protected]
Subject
Re: st: RE: RE: vselect & diff n
Date
Mon, 14 Mar 2011 13:30:34 -0500
Joshua Baur <[email protected]> writes:
> does vselect account for different n's among various models?
> For instance, in surveys with item non response, n's vary for
> different models, can vselect correct for this, in BIC calculation
> for example?
Under the best option, each model is fit on the subset of the data for
which all possible predictors are not missing. So under the best
option, all models have the same n's (number of observations).
Under forward and backward selection, the data for model fitting is also
restricted to only those observations with non-missing values in all
predictors. This is similar to the behavior of -nestreg-.
--Charles Lindsey
*
* 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/