S3RI Seminar - "Informative observation in multi-state models", Dr Andrew Titman (Lancaster University) Seminar

Event details

Data on multi-state disease processes often arise through intermittent observation of disease status at clinic visit times. This leads to interval-censored or panel-observed data. Standard analyses for such data usually assume that the examination times are non-informative of the disease process, meaning they are ignorable. However if clinic visits are potentially self-initiated and the disease is symptomatic, there is a risk that attendances will arise because a patient's condition has deteriorated leading to a form of selection bias. The talk will give an overview of existing approaches for dealing with informative observation times and the challenges to be overcome. There are analogies and connections with methods for missing data, but the methodology is less developed and informative observation is more often an issue of excess, rather than missing, observations. Focus will be given to methods for diagnosing the presence of informative observation and joint modelling approaches involving simultaneous modelling of the disease and visit processes. The methods are illustrated on data from post-heart transplantation patients.