Avoiding pitfalls when combining multiple imputation and propensity scores

Overcoming bias due to confounding and missing data is challenging when analyzing observational data. Propensity scores are commonly used to account for the first problem and multiple imputation for the latter. Unfortunately, it is not known how best to proceed when both techniques are required. We...

Full description

Saved in:
Bibliographic Details
Published in:Statistics in medicine 2019-11, Vol.38 (26), p.5120-5132
Main Authors: Granger, Emily, Sergeant, Jamie C., Lunt, Mark
Format: Article
Language:English
Subjects:
Algorithms
Bias
Confidence Intervals
confounding
Data Interpretation, Statistical
Estimates
Missing data
Models, Statistical
Monte Carlo Method
multiple imputation
observational data
Observational Studies as Topic - statistics & numerical data
Propensity Score
propensity scores
simulation study
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Overcoming bias due to confounding and missing data is challenging when analyzing observational data. Propensity scores are commonly used to account for the first problem and multiple imputation for the latter. Unfortunately, it is not known how best to proceed when both techniques are required. We investigate whether two different approaches to combining propensity scores and multiple imputation (Across and Within) lead to differences in the accuracy or precision of exposure effect estimates. Both approaches start by imputing missing values multiple times. Propensity scores are then estimated for each resulting dataset. Using the Across approach, the mean propensity score across imputations for each subject is used in a single subsequent analysis. Alternatively, the Within approach uses propensity scores individually to obtain exposure effect estimates in each imputation, which are combined to produce an overall estimate. These approaches were compared in a series of Monte Carlo simulations and applied to data from the British Society for Rheumatology Biologics Register. Results indicated that the Within approach produced unbiased estimates with appropriate confidence intervals, whereas the Across approach produced biased results and unrealistic confidence intervals. Researchers are encouraged to implement the Within approach when conducting propensity score analyses with incomplete data.
ISSN:0277-6715
1097-0258
DOI:10.1002/sim.8355