[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
Re: st: xtmixed - model fit and modeling questions
I previously wrote:
>> Have a look at the -emonly- and -emiter()- options to -xtmixed-, which
>> select optimization via EM (only) and set the number of EM iterations. Most
>> of the time, if you set the EM iterations large enough you can get a feel
>> for which are the offending variance components (i.e., those that really
>> want to be zero and should be taken out of the model).
>> EM maximization does not use Hessians, hence it doesn't suffer from problems
>> of lack of concavity. The flip side is that it can be very slow to
>> converge, not guaranteed to converge at all, and you don't get standard
>> errors. As a result of this, by default EM is relegated to starting-value
>> duty in -xtmixed-.
and Hillel Alpert <HALPERT@hsph.harvard.edu> then asked:
> Standard errors appear for the fixed effects variables using EM (only). Are
> these valid? How can you tell which variables should be 0, by lack of
> convergence (e.g. after ~1000 iterations) or some other way?
Standard errors for the fixed effects are indeed valid, given the values
of the random-effects parameters. That is, they are valid provided that
the random-effects parameters have converged, which is sometimes a tricky
proposition with EM.
As for telling which variables should be zero, if the parameters have
converged or are close to convergence, the variables that "should be zero"
will have values close to zero.
* For searches and help try: