Sy. Lee et Sy. Tsang, Constrained maximum likelihood estimation of two-level covariance structure model via EM type algorithms, PSYCHOMETRI, 64(4), 1999, pp. 435-450
In this paper, the constrained maximum likelihood estimation of a two-level
covariance structure model with unbalanced designs is considered. The two-
level model is reformulated as a single-level model by treating the group l
evel latent random Vectors as hypothetical missing-data. Then, the popular
EM algorithm is extended to obtain the constrained maximum likelihood estim
ates. For general nonlinear constraints, the multiplier method is used at t
he M-step to find the constrained minimum of the conditional expectation. A
n accelerated EM gradient procedure is derived to handle linear constraints
. The empirical performance of the proposed EM type algorithms is illustrat
ed by some artifical and real examples.