[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
Re: st: calculating a loglikelihood in regress
Dan MacNulty <email@example.com> asks:
> Does anyone know if it's possible to calculate a loglikelihood value from
> regress? I tried to download and implement the command "reglike", but I was
> unsuccessful. Perhaps someone is aware of an up-to-date alternative, or can
> provide further instruction on how to use the reglike procedure. Any
> insights would be much appreciated.
-regress- saves this information in e(ll), although it does not display it.
. sysuse auto
. regress mpg weight
. display e(ll)
Of course, if you want this sort of thing displayed, you could always type
. xtmixed mpg weight
. xtmixed mpg weight, reml
if you want the likelihood associated with the "N-k" divided residual error,
rather than the ML residual error, which merely divides by N. -regress-
gives the latter, by the way.
* For searches and help try: