Multilevel modeling

Abstract

Mortality is the most frequently modeled outcome in injury research. It is easy to recognize, relatively free from measurement error, and fundamentally interesting. Injury researchers in public health or clinical medicine have become familiar with logistic regression as a standard way to model a binary outcome like mortality (or alternatively survival). Many other outcomes encountered in injury research can also be considered binary, such as the occurrence of a serious complication or an extended length of stay in hospital.