Nonparametric and Semiparametric Regression Analysis of Group Testing Samples

• Activity Number: 597
• Type: Contributed
• Date/Time: Wednesday, August 7, 2013 : 2:00 PM to 3:50 PM
• Sponsor: Section on Nonparametric Statistics
• Author(s): Mingyu Li*+ and Min-ge Xie
• Companies: Celgene and Rutgers University
• Keywords: Group testing ; EM algorithm ; Smoothing ; Generalized linear models ; Penalized maximum likelihood

Abstract

This paper develops a general methodology of nonparametric and semiparametric regression for group testing data, relating group testing responses to covariates at individual level. We fit nonparametric and semiparametric models and obtain estimators of the parameters and the nonparametric regression function by maximizing penalized likelihood function. For implementation, we develop a modified EM algorithm with individual responses as complete data and observed group testing responses as observed data. Numerical results based on simulations and chlamydia data collected in a Nebraska study show that our estimation methods perform well for estimating both the individual probability of positive outcome and the prevalence rate in the population.