University of Cambridge > > sjm247's list > Understanding longitudinal risk factor analysis in asymptomatic disease - a role for artificial datasets?

Understanding longitudinal risk factor analysis in asymptomatic disease - a role for artificial datasets?

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Steph Moore.

In population-based epidemiology, large cohorts are followed for long periods. Regular assessments are performed but they are often widely spaced in time, making the exact timing of the onset of asymptomatic disease troublesome. Also, the follow-up duration may differ considerably between participants. Hence, neither Cox regression nor logistic regression is optimal for risk factor analysis. Despite large sample sizes, confidence intervals of risk estimates resulting from either Cox or logistic regression are often very wide, hampering subgroup analyses and the assessment of interactions. Use of an artificially generated dataset instead of data from a real cohort gives full control of all relevant aspects, enabling a better understanding of observations done in real data. The development of such an artificial dataset for glaucoma and some applications will be presented.

Nomdo Jansonius is professor of ophthalmology at the University Medical Centre Groningen in the Netherlands and is principal investigator for the glaucoma arm of the Rotterdam Study. His background includes masters degrees in physics and medicine, a PhD undertaken jointly between the University of Groningen and University of Cambridge, and post-doctoral training in epidemiology and statistics. His current research interests include glaucoma, perimetry and physiological optics.

Lunch will be provided

This talk is part of the sjm247's list series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.


© 2006-2024, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity