Joint modelling of repeated measurement and event time data in clinical research
2 September 2013, University of Northumbria, Newcastle (as part of RSS 2013 Conference)
Presented by Robin Henderson, Paula Williamson, Catrin Tudur-Smith, Pete Philipson and Ruwanthi Kolamunnage-Dona
In many biomedical studies the outcome on each subject includes a time sequence of repeated measurements at pre-specified times and one or more time to event outcomes. One of several examples and a common situation is where some individuals withdraw or dropout from the study before completing the measurement schedule but the dropout may be non-ignorable or informative. In such cases, the repeated measurement outcome data alone may not reflect a genuine change over time, it may be an artefact caused by selective dropout which could result in a biased comparison between the treatment groups.
Joint modelling is a novel statistical method to investigate how the patterns over time in repeated measurement outcome (e.g. biomarker) relate to prognosis for the patient and in particular to the timing of clinically significant events or dropout. These models take into account errors in the repeated measurement measurements and unexplained variation between individuals, in order to distinguish between systematic relationship patterns and chance variation in observed data. However, simple approaches remain widespread amongst medical researchers, leading to inefficient analysis and the potential for important predictive relationships to be missed.
This workshop aims to provide the research community with an awareness of the potential problems in commonly occurring clinical and observational settings, the inefficiency of simple approaches, the practical relevance of joint modelling, and freely available, documented software.
For more information and to register, please visit http://www.rssconference.org.uk/courses-workshops/
You may leave the list at any time by sending the command
SIGNOFF allstat
to [log in to unmask], leaving the subject line blank.
|