[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
Re: st: RE: impute: too many variables specified
At 06:07 PM 11/18/2004 +0000, Nick Cox wrote:
I was thinking this sounded familiar. Jeff Pitblado discussed it here and
basically said don't try to increase the limit yourself. However, he also
describes a possible -nomissings- option that has indeed since been added
This was asked a while back. I can't remember
the answer but it should be in the archives.
A quite different comment is to ask how much
better your imputation is based on 30+ predictors
rather than 30.
As to why you might want more than 30 predictors -- one example might be
where you have a categorical variable with many categories (resulting in
30+ dummy variables).
* For searches and help try: