Conference Program Home
  My Program

All Times EDT

Abstract Details

Activity Number: 311 - Does Missing Data Affect Outcomes Examined Using Nationally Representative Survey Databases? A Comparison of Traditional and Data Science Approaches
Type: Invited
Date/Time: Tuesday, August 9, 2022 : 2:00 PM to 3:50 PM
Sponsor: Survey Research Methods Section
Abstract #320385
Title: Are Deep Learning Models Superior for Missing Data Imputation in Large Surveys? Evidence from an Empirical Comparison
Author(s): OLANREWAJU MICHAEL AKANDE* and ZHENHUA WANG and Jason Poulos and Fan Li
Companies: Duke University and University of Missouri and Harvard Medical School and Duke University
Keywords: deep learning; hyperparameter selection; missing data; multiple imputation; simulation studies; survey data
Abstract:

Multiple imputation (MI) is a popular method for dealing with missing data in sample surveys. MI by chained equations (MICE) is one of the most widely used MI algorithms for multivariate data, but it lacks theoretical foundation and is computationally intensive. Recently, missing data imputation methods based on deep learning models have been developed with encouraging results in small studies. However, there has been limited research on systematically evaluating their performance in realistic settings compared to MICE, particularly in large-scale surveys. We conduct extensive simulation studies to compare the repeated sampling properties of four machine learning based MI methods: MICE with classification trees, MICE with random forests, generative adversarial imputation network, and MI using denoising autoencoders. We find the deep learning based methods dominate MICE in terms of computational time; however, under the default choice of hyperparameters in the common software packages, MICE with classification trees consistently outperforms the deep learning imputation methods in terms of bias, mean squared error, and coverage under a range of realistic settings.


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

Back to the full JSM 2022 program