Parameter estimation with missing data via equalization-maximization

The expectation-maximization (EM) algorithm is often used in maximum likelihood (ML) estimation problems with missing data. However, EM can be rather slow to converge. In this paper, we introduce a new algorithm for parameter estimation problems with missing data, which we call equalization-maximization (EqM) (for reasons to be explained later). We derive the EqM algorithm in a general context and illustrate its use in the specific case of a Gaussian autoregressive time series with a varying amount of missing observations. In the presented examples, EqM outperforms EM in terms of computational speed, at a comparable estimation performance.