Tweedie Regression Analysis of Determinants of Birth Weight in Navrongo

Abstract

Abstract The study modelled and investigated the determinants of infant birth weight by considering maternal and infant factors as predictors. Monthly data spanning for a period of 37 months were obtained from the Navrongo Health Research Centre of the Navrongo Municipality of the Upper East region of Ghana. In modelling the birth weight of infants, the Tweedie regression model and its counterparts of exponential families (Gaussian, Gamma and inverse Gaussian) of distribution were developed. The performances of these models were evaluated using the Akaike Information Criterion. Based on the Akaike Information Criterion, the Tweedie regression model showed superiority in modelling the determinants of infant birth weight as compared to the other counterparts of the exponential families of distributions. The parameter estimates of the Tweedie regression model found child’s gender and maternal factors (religion, marital status and educational level) to contribute substantially to the birth weight of infants. Also, the study recommends that except for the status of antenatal care, emphasis must be placed on determining the reasons for the decrease in infant birth weight as a result of the maternal factors; parity, delivery type and the age of the mother.