In this 4-days course the participants will be introduced to the concepts of multistate models and will learn how to estimate the essential quantities in the two most frequently encountered data situations: Event-histories, for which the exact times of transitions are known, and panel data, where observations are only made in (more or less) regular intervals, leading to interval-censored data.
The course will start with a brief recap of standard survival analysis on which many of the concepts in multistate modeling are based. Moving beyond two-state models the core concepts will be introduced. Besides the estimation of the key parameters, the transition intensities, derived quantities, such as expected lengths of stay in particular states, will be discussed. Selecting and validating well-fitting models, assessing uncertainty of estimates and illustrative presentation of results will also be covered.
The course will be a mix of lectures and computer practicals using the statistical software R.