Combining Probability and Nonprobability Samples by Using Latent Joint Multivariate Normal Model Mass Imputation

• Activity Number: 489 - Quality of Survey Responses
• Type: Contributed
• Date/Time: Wednesday, August 10, 2022 : 2:00 PM to 3:50 PM
• Sponsor: Survey Research Methods Section
• Author(s): Alexandra Milligan and Sixia Chen and Janis Campbell*
• Companies: University of Oklahoma Health Sciences Center and University of Oklahoma Health Sciences Center and University of Oklahoma Health Sciences Center

Abstract

Nonprobability samples have been used frequently in practice including public health study, economics, education, and political polls. Naïve estimates based on nonprobability samples without any further adjustments may suffer from serious selection bias. Mass imputation has been shown to be effective in practice to improve the representativeness of nonprobability samples. It builds imputation model based on nonprobability samples and generates imputed values for all units in the probability samples. In this paper, we compare two mass imputation approaches including latent joint multivariate normal model mass imputation (e.g. Generalized Efficient Regression-Based Imputation with Latent Processes (GERBIL)) and fully conditional specification (FCS) procedures. Simulation study shows the benefits of GERBIL in terms of balancing the Monte Carlo bias and variance. We further evaluate our proposed method by using Population Assessment of Tobacco and Health (PATH) Study data.