Skip to Content

College of Arts & Sciences
Department of Statistics

Paul Albert Colloquium

Thursday, April 21, 2016 - 2:45pm

Statistics Department Colloquium

Where: LeConte College, Room 210

Speaker: Paul Albert

Affiliation: NIH/NICHD

Title:  Predicting poor pregnancy outcomes from multivariate Ultrasound Fetal Growth data

Abstract: Developing predictors of poor pregnancy outcomes such as small-for-gestational age or preterm birth is important for monitoring pregnant women. We will begin by presenting simple two-stage estimation procedures that approximates a full maximum-likelihood approach for predicting a binary event from multivariate longitudinal growth data (Albert, Statistics in Medicine, 2012). Subsequently, we will present a class of joint models for multivariate growth curve data and a binary event that accommodates a flexible skewed error distribution for the ultrasound measurements and an asymmetric link function relating the longitudinal to the binary process (Kim and Albert, In Press at Biometrics).  Finally, we will present a tree-based approach for identifying subgroups of women who have an enhanced predictive accuracy for predicting a binary event from fetal growth data (Foster, et al., JRSS-A, 2016).