11-16-2012 07:57 PM
I am trying to get white standard errors test in my logistic regression. I read a few articles on the internet and came up with the following code:
proc logistic data = LOG;
model log = lsize lprice lsales roa ato chscaled re_ta re_te bmratio indrev TAX86 TAX03/ acov;
However this "/ acov" does not work. Any idea what I'm doing wrong?
11-16-2012 09:44 PM
This seems to work:
proc surveyreg data=log;
model log = lsize lprice lsales roa ato chscaled re_ta re_te bmratio indrev;
Just checking that is this appropriate for the logistic model.?
11-19-2012 07:41 AM
If the variable "log" is a binary variable, then you may want to look at PROC SURVEYLOGISTIC. If it is a continuous variable, then the SURVEYREG code will be a good start. Be aware, though, that it is NOT a logistic model.
11-21-2012 07:48 AM
This seems to work, just to confirm my sample size is large, so do I put counter as my cluster variable?.
PROC SURVEYLOGISTIC data=log;
model log = lsize lprice lsales roa ato escaled re_ta re_te bmratio indrev;
11-21-2012 08:27 AM
Without knowing the data structure and sampling frame, I can't give a full answer. It does seem like a logical choice for the cluster variable, however.
04-09-2013 02:23 PM
Just to confirm, is it correct then that proc surveyreg with a cluster variable gives White SE's? I can't find anywhere in the documentation for this procedure which actual statistic is used.
04-09-2013 03:18 PM
The default variance estimation is a Taylor series expansion. I don't think this meets the definition of White SE's. The other methods are resampling (jackknife delete one) and Fay's method for balanced replication. So far as I can tell, none of these are robust estimators of the type described by White. However, I would trust the jackknife estimator more than I would a White estimator, as there are weaker assumptions, especially regarding independence.