Generalised Growth Mixture Models will enable us to divide the children into different groups (cluster-analysis style) and fit a different trajectory for each group. In the graph below, the y-axis is the probability of being dry at night. Preliminary analysis using data up to 91 months suggests 4 different groups: normal children, delayed dryness, severely delayed dryness and a relapse group.

Group membership can then be used as either a multinomial outcome or as a predictor for further analysis into the causes/effects of subnormal development of continence. The intention is to produce one methodological paper on the subject of fitting such models and then further epidemiological papers using the resulting groups.