Generalized Divergence Criteria for Model Selection Between Random Walk and Ar(1) Model

Abstract

We introduce a kernel-type estimators of ( ) φ /, v -divergence for continuous distributions. We discuss this approach of goodness-of-fit test for a model selection criterion relative to these divergence measures. Our interest is in the problem to testing for choosing between two models using some informational type statistics (on random walk and autoregressive AR (1)). The limit laws of the estimates and test statistics are given under both the null and the alternative hypotheses. We also describe how to apply estimators and illustrate their efficiency through numerical experiences. DHAKER HAMZA et al. 84