Selection of variables in regression models based on inflated distributions

Regression models based on zero inflated distributions are often used in exploratory data analysis having excess zeroes. The difficulty faced by many researchers is with regard to the selection of covariates to be included in the model. Following the idea of focused information criterion, observed focused information criterion is proposed for model selection. The motivation for this has its roots in the concept of observed Fisher information. Using this criterion, a forward selection procedure is proposed for selection of variables in regression models based on inflated distributions. The procedure is illustrated using a dataset on decayed missing filled teeth (DMFT) index using the modified observed focused information criterion.