[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
RE: st: RE: the impute command
At 06:12 PM 5/19/2004 +0100, Nick Cox wrote:
My theory is that, after recoding to 0/1, the logit and regress approaches
would produce virtually identical results, with the main differences
occurring when the predicted probabilities were very close to .5. I can't
prove this, mind you, but I did try a quick simulation of 1000 cases with a
100 missing values on y and the 0/1 predictions were the same in 99 of the
100 cases. If I had a lot of Xs with a lot of scattered missing data, my
guess is that impute would be far easier to use and would produce very
similar results to doing it the "right" way.
Agreed. The "here" was carrying a lot of weight
in my statement. In general, -logit- is surely
better than -regress- for predicting 0-1 variables;
in that context -round()- should be unproblematic.
Looking at impute.ado, it looks like it might be very easy to have it use
-logit- instead of -regress-; except you'd have to add error checking to
make sure the y var was a dichotomy, and it might take much longer to
run. Not sure it would be worth it.
Of course, I'm still fairly skeptical as whether logit or regress should be
used at all, as opposed to just doing listwise deletion.
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
WWW (personal): http://www.nd.edu/~rwilliam
WWW (department): http://www.nd.edu/~soc
* For searches and help try: