Statistical Methods for Frailty Models: Studies on Old-Age Mortality and Recurrent Events
- M. Böhnstedt
- Tuesday 30 November 2021
2311 GJ Leiden
- Prof. H. Putter
This thesis develops and investigates statistical methodology for two frailty models used in studies of old-age mortality and recurrent events.
In frailty models, the risks of experiencing events like death can differ between individuals due to unobservable characteristics.
The slowing down of human death rates at advanced ages can be explained by such heterogeneity in mortality risks. If individuals with higher mortality risks tend to die earlier, the group of survivors to older ages tends to consist of individuals with lower mortality risks. Old-age mortality has repeatedly been investigated, but empirical studies are often challenged by the scarcity of observations at the oldest ages.
The first part of the thesis therefore examines different methods for assessing the mortality trajectory at old ages in the framework of a specific frailty model. A new powerful tool for detecting an actual slowing down of the death rates is proposed and questions of study design are discussed.
The second part of the thesis focuses on a frailty model for studying recurrent events in the presence of death. The model takes into account the potential association between an individual’s recurrences and mortality, such as if a higher risk of repeated infections is accompanied by a higher mortality risk.
The thesis extends the existing methodology for this model to two common situations of incomplete observations, thereby allowing the model to be used in a wider variety of contexts such as for studying disease events and mortality in elderly populations.
PhD dissertations by Leiden PhD students are available digitally after the defence through the Leiden Repository, that offers free access to these PhD dissertations. Please note that in some cases a dissertation may be under embargo temporarily and access to its full-text version will only be granted later.
Press enquiries (journalists only)
+31 71 527 7211