Is it possible to estimate mixed-effects models using GAUSS?
Models containing both fixed and random effects are particularly useful in settings with longitudinal data or where measurements are made on nested clusters of related statistical units.
1 Answer
0
TSMT offers tscsmt, which can compute either fixed effects or random effects but not mixed-effects models.
The EM algorithm is sometimes used to estimate these models. A classic example of the EM method in GAUSS is James Hamilton's code for estimation of the Markov switching models using the EM algorithm. From his website:
"Programs for estimation of Markov switching models using the EM algorithm. These are written in the GAUSS programming language. They do not require use of the GAUSS numerical optimization procedures and should work with little or no change on any version of GAUSS.."
http://econweb.ucsd.edu/~jhamilto/Markov2.zip
Your Answer
1 Answer
TSMT offers tscsmt, which can compute either fixed effects or random effects but not mixed-effects models.
The EM algorithm is sometimes used to estimate these models. A classic example of the EM method in GAUSS is James Hamilton's code for estimation of the Markov switching models using the EM algorithm. From his website:
"Programs for estimation of Markov switching models using the EM algorithm. These are written in the GAUSS programming language. They do not require use of the GAUSS numerical optimization procedures and should work with little or no change on any version of GAUSS.."
http://econweb.ucsd.edu/~jhamilto/Markov2.zip