Model selection based on penalized ϕ-divergences for multinomial data (original) (raw)

Journal of Computational and Applied Mathematics, 2020

Abstract

Abstract A test approach to the model selection problem for multinomial data based on penalized ϕ -divergences is proposed. The test statistic is a sample version of the difference of the distances between the population and each competing model. The null distribution of the test statistic is derived, showing that it depends on whether the competing models intersect or not and whether certain parameter is positive or not. All possible cases are characterized, and we give rules to decide if a model provides a better explanation for the available data than the other. The practical behavior of the proposal is evaluated by means of an extensive simulation experiment. The method is applied to a real data set related to the classification of individuals according to their social preferences.

Francisca Jiménez Jiménez hasn't uploaded this paper.

Let Francisca know you want this paper to be uploaded.

Ask for this paper to be uploaded.