A Goodness of Fit Test for the Multilevel Logistic Model

Abstract

It is crucial to test the goodness of fit of a model before it is used to make statistical inferences. However, no satisfactory goodness of fit test is available for the case of categorical multilevel data which occur when categorical data are clustered or hierarchical in nature. Hence the aim of this paper is to develop a new goodness of fit test for multilevel binary data based on Hosmer and Lemeshow and Lipsitz et.al. In order to identify the properties of the developed test, simulation studies were carried out to assess the Type I error and the power.

Keywords:

• Binary data
• Hosmer–Lemeshow test
• Multilevel models
• Power
• Simulation
• Type I error.

Mathematics Subject Classification:

• 62F05