Dr. Peng is a biostatistician and Professor in the Department of Public Health Sciences at Queen's University. Dr. Peng's methodology research has focused on: marginal and random effects models for survival data with a cured fraction; semi-parametric estimation methods and model selection for survival models, and statistical models for observational studies. Much of this research has involved Ph.D students, and collaborations with researchers at CCE, NCIC Clinical Trials Group, University of South Carolina, University of Michigan, and NCI, and is applicable in both clinical trials and observational studies.
Title: Model diagnostic methods in mixture cure models
Time and location: 9:00-10:00, August 26, 2016, Room A1138 Innovation park building
Abstract: Model diagnosis, an important issue in statistical modeling, has not yet been addressed adequately for cure models. We focus on mixture cure models in this work and propose some residual-based methods to examine the fit of the mixture cure model, particularly the fit of the latency part of the mixture cure model. The new methods extend the classical residual-based methods to the mixture cure model. Numerical work shows that the proposed methods are capable of detecting lack-of-fit of a mixture cure model, particularly in the latency part, such as outliers, improper covariate functional form, or nonproportionality in hazards if the proportional hazards assumption is employed in the latency part. The methods are illustrated with two real data sets that were previously analyzed with mixture cure models.
Title: Prediction in survival models
Time and Location: 14:00-15:00, September 12, 2016, Room 410 Graduate school building
Abstract: We propose a method to assess the prediction accuracy of a mixture cure model in predicting cure probability based on inverse probability of censoring weights (IPCW) to incorporate the censoring and latent cure status in the data. A simulation study shows that the estimator performs well with finite samples when subjects with censored survival times greater than the largest uncensored time are identified as cured. The simulation study also investigates the performance of the estimator with different thresholds to identify cured subjects. The method is applied to a real data set for assessing prediction accuracy for the cure probabilities.
Title: Statistical computing issues in cure models
Time and Location: 14:00-15:00, September 19, 2016, Room A1101 Innovation park building
Abstract: We mainly discuss the related algorithms in cure models.