Modelling the rate of change in a longitudinal study with missing data, adjusting for contact attempts
- Publisher: University of Warwick. Centre for Research in Statistical Methodology
The Collaborative Ankle Support Trial (CAST) is a longitudinal trial in which interest lies in the rate of\ud improvement, the effectiveness of reminders and potentially informative missingness. A model is proposed for\ud continuous longitudinal data with non-ignorable or informative missingness, taking into account the nature of\ud attempts made to contact initial non-responders. The model combines a non-linear mixed model for the outcome\ud model with a logistic regression model for the reminder process. A sensitivity analysis is used to contrast this\ud model with the traditional selection model, where we adjust for missingness by modelling the missingness process.