Online Program Home
  My Program

All Times EDT

Abstract Details

Activity Number: 76 - Contributed Poster Presentations: Section on Statistics in Epidemiology
Type: Contributed
Date/Time: Monday, August 3, 2020 : 10:00 AM to 2:00 PM
Sponsor: Section on Statistics in Epidemiology
Abstract #313179
Title: Bayesian Frailty Models for Eye Tracking Experiments
Author(s): David Angeles*
Companies: Ohio State Univ
Keywords: heterogeneity

Health warning labels have been found to increase knowledge about the harmful effects of tobacco products. A preliminary eye tracking study was conducted to determine the optimal placement of a health warning label for hookah pipes. Three areas of interest (AOIs) were considered for comparison, namely the base, stem, and hose. Participants in the study viewed images that contained one of four pipes, and one of three warning labels places in one of the AOIs. Normally, summary statistics such average dwell time, proportion of viewing time, and number of visits to a label AOI have been the focus for determining such placement. Although these summary statistics are important, they do not make use of the temporal structure of the data set. We have incorporated time-to-event models to compare viewing conditions with respect to time to first visit to the AOI as well as time between visits. Furthermore, these models can account for the dependencies in observations between participants. However, extra heterogeneity in the hazard due to different pipes cannot be modeled using standard software packages. Therefore, Bayesian models were used to account for both unobserved heterogeneities.

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

Back to the full JSM 2020 program