Online Program Home
My Program

Abstract Details

Activity Number: 484
Type: Topic Contributed
Date/Time: Wednesday, August 3, 2016 : 8:30 AM to 10:20 AM
Sponsor: Biometrics Section
Abstract #319399 View Presentation
Title: Marginal Mean Models for Zero-Inflated Count Data with Spline-Based Semiparametric Estimation
Author(s): David Todem* and Yifan Yang
Companies: Michigan State University and Michigan State University
Keywords: Marginal mean ; Nonparametric ; Caries indices ; Oral health ; Low-income African American ; Sugar consumption

We propose a semiparametric regression model for zero-inflated count data that directly relates covariates to the marginal mean response representing the desired target of inference. The model specifically assumes two semiparametric forms for the log-linear model of the marginal mean and the logistic-linear model of the susceptibility probability, in which the fully linear formulations are replaced with partially linear functions. A Spline-based maximum likelihood estimation method is proposed for both the parametric and the nonparametric components of the model. Large sample properties of the resulting estimators are established under mild regularity conditions. Simulation studies are conducted to evaluate the finite sample performance of the method. Finally, the model is applied to oral health data in low income African-American children to evaluate the effect of sugar intake on caries indices, treating age as an effect modifier.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2016 program

Copyright © American Statistical Association