Abstract

A model for missing data in mixed binary and continuous responses, which can be used on cross-sectional data, is presented. In this model response indicator for the binary response can be dependent on the continuous response. A closed form for the likelihood is found. For data with a complicated pattern of missing responses some new residuals are also proposed. The model of multiplicative heteroscedasticity is used to consider the problem of heteroscedasticity of the continuous response. The model is illustrated on the data of an observational study where the effect of psychological disorder of parents on both the verbal comprehension score and the presence of adverse symptoms in their children are modeled in the presence of missing responses.