Detection of some social parameters on child mortality through joint generalized linear models

Rabindra Nath Das, The University of Burdwan
Shankar Dihidar, Indian Statistical Institute

In general demographic characteristics are positive in nature. In regression models for positive observations analysis can often be based on either the log-normal or the gamma model. Recently log-normal and gamma models are of interest in fitting data arising from quality-improvement experiments. It is known that the gamma model with the constant coefficient of variation and the log-normal model with constant variance often give similar analysis. However, in the analysis of data from quality improvement experiments neither the coefficient of variation nor the variance needs to be constant, so that the two models do not necessarily give similar results. A choice needs to be made between the gamma and the log-normal models. This article analyzes the effects of social factors in children survival times through joint generalized linear models, and many interested social parameters have been detected in its mean and variance model.