Finite mixture distributions, sequential likelihood and the EM algorithm

被引:66
作者
Arcidiacono, P
Jones, JB
机构
[1] Duke Univ, Dept Econ, Durham, NC 27708 USA
[2] SUNY Albany, Dept Econ, Albany, NY 12222 USA
关键词
unobserved heterogeneity; mixture distributions; EM algorithm; dynamic discrete choice;
D O I
10.1111/1468-0262.00431
中图分类号
F [经济];
学科分类号
02 ;
摘要
A popular way to account for unobserved heterogeneity is to assume that the data are drawn from a finite mixture distribution. A barrier to using finite mixture models is that parameters that could previously be estimated in stages must now be estimated jointly: using mixture distributions destroys any additive separability of the log-likelihood function. We show, however, that an extension of the EM algorithm reintroduces additive separability, thus allowing one to estimate parameters sequentially during each maximization step. In establishing this result, we develop a broad class of estimators for mixture models. Returning to the likelihood problem, we show that, relative to full information maximum likelihood, our sequential estimator can generate large computational savings with little loss of efficiency.
引用
收藏
页码:933 / 946
页数:14
相关论文
共 29 条
[1]  
Amemiya T., 1978, Journal of Econometrics, V8, P13, DOI https://doi.org/10.1016/0304-4076(78)90086-6
[2]  
[Anonymous], 2000, WILEY SERIES PROBABI
[3]  
ARCIDIACONO P, 2002, UNPUB AFFIRMATIVE AC
[4]   Life cycle schooling and dynamic selection bias: Models and evidence for five cohorts of American males [J].
Cameron, SV ;
Heckman, JJ .
JOURNAL OF POLITICAL ECONOMY, 1998, 106 (02) :262-333
[5]   The dynamics of educational attainment for black, Hispanic, and white males [J].
Cameron, SV ;
Heckman, JJ .
JOURNAL OF POLITICAL ECONOMY, 2001, 109 (03) :455-499
[6]   PARTIAL LIKELIHOOD [J].
COX, DR .
BIOMETRIKA, 1975, 62 (02) :269-276
[7]   MAXIMUM LIKELIHOOD FROM INCOMPLETE DATA VIA EM ALGORITHM [J].
DEMPSTER, AP ;
LAIRD, NM ;
RUBIN, DB .
JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-METHODOLOGICAL, 1977, 39 (01) :1-38
[8]   Why youths drop out of high school: The impact of preferences, opportunities, and abilities [J].
Eckstein, Z ;
Wolpin, KI .
ECONOMETRICA, 1999, 67 (06) :1295-1339
[9]  
EFRON B, 1982, ANN STAT, V10, P323, DOI 10.1214/aos/1176345777
[10]  
Everitt B. S., 1981, FINITE MIXTURE DISTR