[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
Re: st: Log pseudo-likelihood
At 12:05 PM 5/28/2004 -0400, Marwan Khawaja wrote:
You will see that when using robust standard errors (which are sometimes
forced by the use of options such as cluster, or pweights). Are you
encountering it in other cases? There is some discussion of this on p. 28
of the Stata 8 Survey Data Manual. It says that "pseudo-maximum likelihood
methods" (which get used with robust SEs) are not "true likelihoods" and
hence "standard LR tests are no longer valid".
Sometimes the output from logit reports log-pseudo likelihood instead of
I do not know why -- Where can I find documentation of this?
I am using stata 8.2 on ms windows.
Incidentally, there must have been some fine-tuning of this since the
manuals came out. P. 305 of the Reference Manual G-M gives an example of
logistic regression using robust standard errors. It reports the log
likelihood; but when I replicate the example it reports the log
pseudo-likelihood. There are also differences in the robust standard
errors reported and in the Wald chi-square.
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: