ABSTRACT
This chapter explores both a logistic regression and a linear regression to the data using the General Health Questionnaire score as the single explanatory variable. The logistic regression model is a generalized linear model that can be used to assess the effects of a set of explanatory variables on a binary response variable. The estimated parameters in the logistic regression model can be interpreted in terms of odds and odds ratios. Parsimonious models can be selected by the same approach as for the multiple linear regression model. As with the fitting of multiple linear regression models, the aim when fitting logistic regression models is to select the most parsimonious model that gives an adequate description of the data. The chapter provides a logistic model for the probability of responding yes in the survey with work, tenure, accommodation type, and age as explanatory variables.
