Tags

Type your tag names separated by a space and hit enter

Variance reduction in randomised trials by inverse probability weighting using the propensity score.
Stat Med. 2014 Feb 28; 33(5):721-37.SM

Abstract

In individually randomised controlled trials, adjustment for baseline characteristics is often undertaken to increase precision of the treatment effect estimate. This is usually performed using covariate adjustment in outcome regression models. An alternative method of adjustment is to use inverse probability-of-treatment weighting (IPTW), on the basis of estimated propensity scores. We calculate the large-sample marginal variance of IPTW estimators of the mean difference for continuous outcomes, and risk difference, risk ratio or odds ratio for binary outcomes. We show that IPTW adjustment always increases the precision of the treatment effect estimate. For continuous outcomes, we demonstrate that the IPTW estimator has the same large-sample marginal variance as the standard analysis of covariance estimator. However, ignoring the estimation of the propensity score in the calculation of the variance leads to the erroneous conclusion that the IPTW treatment effect estimator has the same variance as an unadjusted estimator; thus, it is important to use a variance estimator that correctly takes into account the estimation of the propensity score. The IPTW approach has particular advantages when estimating risk differences or risk ratios. In this case, non-convergence of covariate-adjusted outcome regression models frequently occurs. Such problems can be circumvented by using the IPTW adjustment approach.

Authors+Show Affiliations

Department of Epidemiology and Preventive Medicine, Monash University, Melbourne, Victoria, Australia; Melbourne School of Population and Global Health, University of Melbourne, Victoria, Australia.No affiliation info availableNo affiliation info available

Pub Type(s)

Journal Article
Research Support, Non-U.S. Gov't

Language

eng

PubMed ID

24114884

Citation

Williamson, Elizabeth J., et al. "Variance Reduction in Randomised Trials By Inverse Probability Weighting Using the Propensity Score." Statistics in Medicine, vol. 33, no. 5, 2014, pp. 721-37.
Williamson EJ, Forbes A, White IR. Variance reduction in randomised trials by inverse probability weighting using the propensity score. Stat Med. 2014;33(5):721-37.
Williamson, E. J., Forbes, A., & White, I. R. (2014). Variance reduction in randomised trials by inverse probability weighting using the propensity score. Statistics in Medicine, 33(5), 721-37. https://doi.org/10.1002/sim.5991
Williamson EJ, Forbes A, White IR. Variance Reduction in Randomised Trials By Inverse Probability Weighting Using the Propensity Score. Stat Med. 2014 Feb 28;33(5):721-37. PubMed PMID: 24114884.
* Article titles in AMA citation format should be in sentence-case
TY - JOUR T1 - Variance reduction in randomised trials by inverse probability weighting using the propensity score. AU - Williamson,Elizabeth J, AU - Forbes,Andrew, AU - White,Ian R, Y1 - 2013/09/30/ PY - 2012/12/11/received PY - 2013/07/30/revised PY - 2013/09/03/accepted PY - 2013/10/12/entrez PY - 2013/10/12/pubmed PY - 2014/12/15/medline KW - baseline adjustment KW - variance estimation SP - 721 EP - 37 JF - Statistics in medicine JO - Stat Med VL - 33 IS - 5 N2 - In individually randomised controlled trials, adjustment for baseline characteristics is often undertaken to increase precision of the treatment effect estimate. This is usually performed using covariate adjustment in outcome regression models. An alternative method of adjustment is to use inverse probability-of-treatment weighting (IPTW), on the basis of estimated propensity scores. We calculate the large-sample marginal variance of IPTW estimators of the mean difference for continuous outcomes, and risk difference, risk ratio or odds ratio for binary outcomes. We show that IPTW adjustment always increases the precision of the treatment effect estimate. For continuous outcomes, we demonstrate that the IPTW estimator has the same large-sample marginal variance as the standard analysis of covariance estimator. However, ignoring the estimation of the propensity score in the calculation of the variance leads to the erroneous conclusion that the IPTW treatment effect estimator has the same variance as an unadjusted estimator; thus, it is important to use a variance estimator that correctly takes into account the estimation of the propensity score. The IPTW approach has particular advantages when estimating risk differences or risk ratios. In this case, non-convergence of covariate-adjusted outcome regression models frequently occurs. Such problems can be circumvented by using the IPTW adjustment approach. SN - 1097-0258 UR - https://www.unboundmedicine.com/medline/citation/24114884/Variance_reduction_in_randomised_trials_by_inverse_probability_weighting_using_the_propensity_score_ L2 - https://dx.doi.org/10.1002/sim.5991 DB - PRIME DP - Unbound Medicine ER -