Robust estimation of location and concentration parameters for the von Mises-Fisher distribution

TL;DR

This paper introduces robust estimation methods for the von Mises-Fisher distribution's parameters, using density power divergences, with algorithms, simulations, and real data application to improve robustness over traditional maximum likelihood estimation.

Contribution

It proposes two novel families of robust estimators for the von Mises-Fisher distribution's parameters, addressing non-robustness of MLE and enabling simultaneous estimation.

Findings

Proposed estimators outperform MLE in robustness.

Algorithms effectively compute estimates.

Simulation and real data demonstrate practical utility.

Abstract

Robust estimation of location and concentration parameters for the von Mises-Fisher distribution is discussed. A key reparametrisation is achieved by expressing the two parameters as one vector on the Euclidean space. With this representation, we first show that maximum likelihood estimator for the von Mises-Fisher distribution is not robust in some situations. Then we propose two families of robust estimators which can be derived as minimisers of two density power divergences. The presented families enable us to estimate both location and concentration parameters simultaneously. Some properties of the estimators are explored. Simple iterative algorithms are suggested to find the estimates numerically. A comparison with the existing robust estimators is given as well as discussion on difference and similarity between the two proposed estimators. A simulation study is made to evaluate finite sample performance of the estimators. We consider a sea star dataset and discuss the selection of the tuning parameters and outlier detection.