Rate My Professor Xiaoyan Lin

Lin's research centers on Bayesian statistics applied to survival analysis and medical diagnostic accuracy and ROC analysis, with emphasis on methods for censored and ordinal data, including latent graphical models for ordinal dependencies, neural networks for ordinal classification, and Bayesian Additive Regression Trees for censored survival data. Key publications feature “Bayesian proportional hazards model for current status data with monotone splines” in Computational Statistics & Data Analysis (2011), “A semiparametric probit model for case 2 interval-censored failure time data” in Statistics in Medicine (2010), “A Bayesian proportional hazards model for general interval-censored data” in Lifetime Data Analysis (2015), and “Bayesian hierarchical latent class models for estimating diagnostic accuracy” in Statistical Methods in Medical Research (2020). She has participated in an NIH grant on agreement webs, presented at Joint Statistical Meetings, ENAR, and O-Bayes conferences, and reviewed for journals such as Computational Statistics and Data Analysis. Awards include the Superior Graduate Student Achievement Award and JSM Travel Award from the University of Missouri-Columbia Graduate School (2006-2007).