Applying Multiple Imputation Using External Calibration to Propensity Score Estimation

• Activity Number: 3
• Type: Invited
• Date/Time: Sunday, August 3, 2014 : 2:00 PM to 3:50 PM
• Sponsor: Social Statistics Section
• Author(s): Elizabeth A. Stuart*+ and Yenny Webb Vargas and David Lenis
• Companies: Johns Hopkins Bloomberg School of Public Health and Johns Hopkins Bloomberg School of Public Health and Johns Hopkins Bloomberg School of Public Health
• Keywords: causal inference ; measurement error ; non-experimental study

Abstract

Propensity score methods are commonly used to estimate causal effects in non-experimental studies. Existing propensity score methods assume that covariates are measured without error but covariate measurement error is likely common. This work investigates Multiple Imputation using External Calibration (MIEC) to account for covariate measurement error in propensity score estimation. MIEC uses a main study sample and a calibration dataset that includes observations of the true covariate (X) as well as the version measured with error (W). MIEC creates multiple imputations of X in the main study sample, using information on the joint distribution of X, W, other covariates, and the outcome of interest, from both the calibration and the main data. In simulation studies we found that MIEC estimates the treatment effect almost as well as if the true covariate X were available. We also found that the outcome must be used in the imputation process, a finding related to the idea of congeniality in the multiple imputation literature. We illustrate MIEC using an example estimating the effects of early intensive intervention for young children with autism.