Unsupervised Mixture Estimation via Approximate Maximum Likelihood based on the Cram\'er - von Mises distance

TL;DR

This paper introduces an approximate maximum likelihood estimation method for mixture models with dynamic weights, using the Cramér-von Mises distance, which improves estimation accuracy especially for complex distributions like the lognormal-generalized Pareto.

Contribution

It develops a novel hybrid estimation procedure combining standard MLE with AMLE based on the Cramér-von Mises distance for mixture models with intractable normalizing constants.

Findings

The proposed method outperforms standard MLE in simulations.

It effectively estimates complex mixture distributions like the lognormal-GP.

Real-data applications demonstrate practical advantages of the approach.

Abstract

Mixture distributions with dynamic weights are an efficient way of modeling loss data characterized by heavy tails. However, maximum likelihood estimation of this family of models is difficult, mostly because of the need to evaluate numerically an intractable normalizing constant. In such a setup, simulation-based estimation methods are an appealing alternative. The approximate maximum likelihood estimation (AMLE) approach is employed. It is a general method that can be applied to mixtures with any component densities, as long as simulation is feasible. The focus is on the dynamic lognormal-generalized Pareto distribution, and the Cram\'er - von Mises distance is used to measure the discrepancy between observed and simulated samples. After deriving the theoretical properties of the estimators, a hybrid procedure is developed, where standard maximum likelihood is first employed to determine the bounds of the uniform priors required as input for AMLE. Simulation experiments and two real-data applications suggest that this approach yields a major improvement with respect to standard maximum likelihood estimation.