On Some Recent Results on Recurrent Events Modelling
Recurrent event data is often observed in a wide variety of disciplines including the biomedical, public health, engineering, economic, actuarial science, and social science settings.  Examples are chronic disease recurrences, cancer tumor recurrence, repeated hospitalization, successive non-life insurance claims, repeated failures of an AC machine. Consider n independent units that are monitored for the occurrence of a recurrent event.  Statistical inferences pertaining to the inter event time distribution function F, its functional, or the cumulative hazard rate function are often of interest for these type of data. In this talk, I will present some recent results pertaining to the modelling and analysis of the aforementioned data.  I will first discuss results on the chi-square goodness of fit test for F based on random cells, where F is assumed to belong to some parametric family of distributions. The lecture will proceed with the problem of estimating the baseline hazard function in a Cox-type regression model for recurrent events. A Nelson-Aalen type estimator of the baseline intensity function that takes into account the change in age of a unit due to interventions allows for the possibility of the unit receiving a life supplement and provides a mechanism for researchers to incorporate time-dependent covariates  will be presented.  Asymptotic properties of the estimators as well as those of the proposed test will be discussed. The finite sample properties of the inference procedures are investigated via simulation studies.

Bio: After his Master degree in Statistics at University of Michigan-Ann Arbor, Dr. Adekpedjou attended University of South Carolina where he received a PhD in Statistics in 2007 under the supervision of Dr. Edsel Pe{\~n}a. He then joined the faculty at Missouri University of Science and Technology (Missouri S\&T) (formerly University of Missouri-Rolla). He was promoted to the rank of Associate Professor of Statistics with Tenure in summer 2013. Dr. Adekpedjou research interests include survival analysis, recurrent events, reliability theory, complex survey data, multiple hypotheses testing,  and actuarial science. Dr. Adekpedjou is the director of the Actuarial Science program at Missouri S\&T. His honors include two campus-wide outstanding teaching awards at Missouri S\&T in 2011 and 2012, and was also awarded the outstanding graduate student researcher award in 2006 from the Department of Statistics at University of South Carolina. Dr. Adekpedjou became Associate Editor of South African Journal of Statistics as of December 2013. He is currently advising many PhD and Master students at Missouri S\&T.