Robust Generalized Linear Models (GLM) using Mixtures

Robust generalized linear models (GLM) using a mixture method, as described in Beath (2018) . This assumes that the data are a mixture of standard observations, being a generalised linear model, and outlier observations from an overdispersed generalized linear model. The overdispersed linear model is obtained by including a normally distributed random effect in the linear predictor of the generalized linear model.