ABSTRACT
The summary measure approach to the analysis of longitudinal data described in the previous chapter sometimes provides a useful first step in making inferences about the data, but it is really only ever a first step; a more complete and a more appropriate analysis will involve fitting a suitable model to the data and estimating parameters that link the explanatory variables of interest to the repeated measures of the response variable. The main objective in longitudinal studies is to characterise change in the repeated values of the response variable and to determine the explanatory variables most associated with any change.
