Nonparametric Maximum Likelihood Estimation of Semiparametric Regression Models With Censored Data

Title:  Nonparametric Maximum Likelihood  Estimation of Semiparametric Regression Models With Censored Data


Speaker : Professor Danyu Lin (University of North Carolina at Chapel Hill)


Date: 16:00-17:00pm, June 9, 2014


Place: Conference Room A304, Department of Mathematical Sciences


Abstract:  Semiparametric regression models provide an attractive way to formulate the effects of covariates on potentially censored failure times.

    The partial likelihood, which works beautifully for the Cox proportional hazards model with univariate failure time data, is not tractable for general transformation models for univariate failure time data,  random-effects models for multivariate failure time data, or joint models for repeated measures and failure times. Nonparametric maximum likelihood estimation (NPMLE) provides an elegant and powerful solution to the statistical inference for such models.

    The presence of infinite-dimensional parameters poses considerable theoretical and computational challenges. We show that the NPMLE is consistent,  asymptotically normal and asymptotically efficient under mild conditions. We develop simple and stable numerical techniques to implement the corresponding inference procedures. Illustrations with real medical studies are provided.


Profile of speakerDanyu Lin is the Dennis Gillings Distinguished Professor of Biostatistics at the University of North Carolina at Chapel Hill. Professor Lin is an internationally renowned statistician who has made fundamental contributions to many areas of statistics, including survival analysis and statistical genetics. He has published over 150 peer-reviewed papers, most of which appeared in top statistical journals. Several of his methods have been incorporated into commercial software packages, such as SAS, S-Plus and STATA, and widely used in practice. Professor Lin is on Thomson ISI's list of Highly Cited Researchers in Mathematics. He is a former recipient of the Mortimer Spiegelman Gold Medal from the American Public Health Association and a Fellow of both the American Statistical Association and the Institute of Mathematical Statistics. He currently serves as an Associate Editor of Biometrika and Journal of the American Statistical Association.


Contact Ying Yang