Checking Multistate Models Under Intermittent Observations

• Activity Number: 125
• Type: Contributed
• Date/Time: Monday, August 4, 2014 : 8:30 AM to 10:20 AM
• Sponsor: SSC
• Author(s): Narges Nazeri Rad*+ and Jerald F. Lawless
• Companies: University of Waterloo and University of Waterloo
• Keywords: intermittent observation ; Markov multistate models ; prevalence probabilities

Abstract

Multistate models are widely used for describing life history processes. In studies where individuals are observed continuously, the transition times between states are known exactly. However, when individuals are observed intermittently, transition times and even the states visited between successive observations, may be unknown. Irregular intermittent observation is a special case of intermittent observation where the observation times vary across individuals. There are considerable Challenges in checking models with irregular observation schemes, since there is a strong possibility that this irregularity may be induced by the dependency of inter-visit times on previous process history, and some existing model checking methods are not designed to accommodate dependent observation times. In this talk, we discuss the estimation of marginal process features such as prevalence functions when there are dependent observation times, and apply this to model checking. We present an application involving viral load dynamics in HIV-positive persons treated with combination antiretroviral therapy.