Testing in logistic regression models based on φφ-divergences measures

In this paper, we consider inference based on very general divergence measures under assumptions of a logistic regression model. We use the minimum φφ-divergence estimator in a φφ-divergence statistic, which is the basis of some new statistics, for solving the classical problems of testing in a logistic regression model. A diagnostic analysis is developed based on the new estimators and test statistics.