M. Menendez et al., DIVERGENCE-BASED ESTIMATION AND TESTING OF STATISTICAL-MODELS OF CLASSIFICATION, Journal of Multivariate Analysis, 54(2), 1995, pp. 329-354
The problems of estimating parameters of statistical models for catego
rical data, and testing hypotheses about these models are studied. Asy
mptotic properties of estimators minimizing phi-divergence between the
oretical and empirical vectors of means are established. Asymptotic di
stributions of phi-divergences between empirical and estimated vectors
of means are explictly evaluated, and tests based on these statistics
are studied. The paper extends results previously established in this
area. (C) 1995 Academic Press, Inc.