A Note on NPML Estimation for Exponential Family Regression Models with Unspecified Dispersion Parameter

Abstract

Nonparametric maximum likelihood (NPML) estimation for exponential families with unspecified dispersion parameter ? suffers from computational instability, which can lead to highly fluctuating EM trajectories and suboptimal solutions, in particular when ? is allowed to vary over mixture components. In this paper, a damped version of the EM algorithm is proposed to cope with these problems.