Online Program Home
My Program

Abstract Details

Activity Number: 705
Type: Contributed
Date/Time: Thursday, August 4, 2016 : 10:30 AM to 12:20 PM
Sponsor: Survey Research Methods Section
Abstract #320008
Title: Comparison of Multiple Imputation Methods for Categorical Survey Items with High Missing Rates: Application to the Family Life, Activity, Sun, Health, and Eating Study
Author(s): Benmei Liu* and Erin Hennessy and April Oh and Linda Nebeling
Companies: National Cancer Institute and National Cancer Institute and National Cancer Institute and National Cancer Institute
Keywords: perceptional categorical data ; high missing rates ; weighted sequential hotdeck ; sequential regression multivariate imputation
Abstract:

The Family Life, Activity, Sun, Health and Eating (FLASHE) study is a National Cancer Institute sponsored survey that examines psychosocial, generational (parent-teen), and environmental correlates of cancer-preventive behaviors. Data was collected in two web surveys (diet focused and physical activity focused) in 2014 from dyads of caregivers and their adolescent children aged 12-17. After data collection was completed, eight variables from the parent physical activity survey were found missing for approximately half of the sample because of a system programming error in the web-based data collection tool. To avoid potential bias and loss in efficiency in estimation and inference involving those variables, we considered and compared multiple imputation methods including the Sequential Regression Multivariate Imputation Algorithm and the Weighted Sequential Hotdeck to accurately impute the missing values for those variables. This paper describes the approaches used in this imputation and evaluates the methods by comparing the distributions of the original and the imputed data. A simulation study using the observed data is also conducted as part of the model diagnostics.


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

Back to the full JSM 2016 program

 
 
Copyright © American Statistical Association