Online Program Home
My Program

Abstract Details

Activity Number: 32 - Longitudinal/Correlated Data I
Type: Contributed
Date/Time: Sunday, July 29, 2018 : 2:00 PM to 3:50 PM
Sponsor: Biometrics Section
Abstract #328919 Presentation
Title: Rank-Tracking Probabilities of Bivariate Dependent Variables in Longitudinal Studies
Author(s): Seonjin Kim* and Hyunkeun Cho and Colin O. Wu
Companies: Miami University and University of Iowa and National Heart, Lung and Blood Institute, NIH
Keywords: Bivariate response; Conditional distribution; Longitudinal data; Kernel estimation; Tracking ability

We proposed a novel methodology to estimate rank-tracking probability for bivariate response vector. The rank-tracking probability can evaluate the risk of future disease based on an individuals' current health condition and thus proper intervention can be provided to reduce the risk. A quantile regression based approach is adopted to estimate the conditional distribution of bivariate response variable and the rank-tracking probability. National Growth and Health Study data is analyzed using the proposed procedure to compute the probability that a preadolescent ten-year-old girl will be diagnosed with hypertension at age 18 (late adolescence), based on characteristics she exhibits at ten years old, including her BMI, height, race and cardiovascular conditions.

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

Back to the full JSM 2018 program