Abstract:

Many systems experience recurrent events.  Recurrence data are collected to analyze quantities of interest, such as the mean cumulative number of events.  Methods of analysis are available for recurrence data with left and/or right censoring.  Due to practical constraints, however, recurrence data are sometimes recorded only in windows.  Between the windows, there are gaps over which the process cannot be observed.  This paper extends existing statistical methods, both nonparametric and parametric, to window-observation recurrence data.  The nonparametric estimator requires minimum assumptions, but will be inconsistent if the size of the risk set is not positive over the entire period of interest.  There is no such difficulty when using a parametric model for the recurrence data. For cases in which the size of the risk set is zero for some periods of time, we propose and compare two alternative hybrid estimators. The methods are illustrated with two example applications.

This is joint work with Dr. William Q. Meeker and Dr. Huaiqing Wu.