Online Program Home
My Program

Abstract Details

Activity Number: 660 - Machine Learning: Advances and Applications
Type: Contributed
Date/Time: Thursday, August 1, 2019 : 10:30 AM to 12:20 PM
Sponsor: Section on Statistical Learning and Data Science
Abstract #306758 Presentation
Title: Classification and Regression Tree Analysis for Participation in Surveys with Physical Measurements
Author(s): Kelly Diecker and Richard (Lee) Harding*
Companies: ICF
Keywords: bio-specimen collection; survey research; participation willingness; variable selection
Abstract:

Adding physical measures and bio-specimen collection to self-reported survey data is becoming increasingly popular in health surveys. While these measures greatly enrich the data’s utility, there is scant research on the public’s willingness to give us this type of information. We surveyed nearly 2,000 US adults from a mobile panel to model willingness to participate in health studies that include height and weight, blood pressure, finger stick blood draws by a health representative, self-collected waist circumference, and measures collected by installing an app on a respondent’s smartphone. Predictors include demographics, health, and lifestyle factors. We compare logistic regression and classification tree analysis to assess the efficacy of each method in predicting willingness to provide physical measures and bio-specimens across types of health data collected. The methodology may improve health survey design, mode, and respondent segmentation.


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

Back to the full JSM 2019 program