Open Access
February 2001 Convex Models, MLS and Misspecification
Valentin Patilea
Ann. Statist. 29(1): 94-123 (February 2001). DOI: 10.1214/aos/996986503


We analyze the asymptotic behavior of maximum likelihood estimators (MLE) in convex dominated models when the true distribution generating the independent data does not necessarily belong to the model. Inspired by the Hellinger distance and its properties, we introduce a family of divergences (contrast functions) which allow a unified treatment of well- and misspecified convex models. Convergence and rates of convergence of the MLE with respect to our divergences are obtained from inequalities satisfied by these divergences and results from empirical process theory (uniform laws of large numbers and maximal inequalities). As a particular case we recover existing results for Hellinger convergence of MLE in well-specified convex models. Four examples are considered: mixtures of discrete distributions, monotone densities, decreasing failure rate distributions and a finite-dimensional parametric model.


Download Citation

Valentin Patilea. "Convex Models, MLS and Misspecification." Ann. Statist. 29 (1) 94 - 123, February 2001.


Published: February 2001
First available in Project Euclid: 5 August 2001

zbMATH: 1029.62020
MathSciNet: MR1833960
Digital Object Identifier: 10.1214/aos/996986503

Primary: 62A10
Secondary: 62F12 , 62G20

Keywords: convex models , empirical process , maximum likelihood , misspecification

Rights: Copyright © 2001 Institute of Mathematical Statistics

Vol.29 • No. 1 • February 2001
Back to Top