Advanced statistics: The propensity score - A method for estimating treatment effect in observational research

Craig Newgard, Jerris R. Hedges, Melanie Arthur, Richard Mullins

Research output: Contribution to journalArticle

131 Citations (Scopus)

Abstract

Observational studies assessing the effect of a particular treatment or exposure may be subject to bias, which can be difficult to eliminate using standard analytic techniques. Multivariable models are commonly used in observational research to assess the relationship between a certain exposure or treatment and an outcome, while adjusting for important variables necessary to ensure comparability between the groups. Large differences in the observed covariates between two study groups may exist in observational studies in which the investigator has no control over who was allocated to each treatment group, and these differences may lead to biased estimates of treatment effect. When there are large differences in important prognostic characteristics between the treatment groups, adjusting for these differences with conventional multivariable techniques may not adequately balance the groups, and the remaining bias may limit valid causal inference. Use of a propensity score, described as a conditional probability that a subject will be "treated" based on an observed group of covariates, may better adjust covariates between the groups and reduce bias. The purpose of this article is to describe the use of propensity scores to adjust for bias when estimating treatment effects in observational research and to compare use of this technique with conventional multivariable regression. The authors present three methods for integrating propensity scores into observational analyses using a database collected on head-injured trauma patients. The article details the methods for creating a propensity score, analyzing data with the score, and explores differences between propensity score methods and conventional multivariable methods, including potential benefits and limitations. Graphical representations of the analyses are provided as well.

Original languageEnglish (US)
Pages (from-to)953-961
Number of pages9
JournalAcademic Emergency Medicine
Volume11
Issue number9
DOIs
StatePublished - Sep 2004

Fingerprint

Propensity Score
Research
Observational Studies
Therapeutics
Craniocerebral Trauma
Research Personnel
Databases

Keywords

  • bias
  • propensity score
  • transfer
  • trauma

ASJC Scopus subject areas

  • Emergency Medicine

Cite this

Advanced statistics : The propensity score - A method for estimating treatment effect in observational research. / Newgard, Craig; Hedges, Jerris R.; Arthur, Melanie; Mullins, Richard.

In: Academic Emergency Medicine, Vol. 11, No. 9, 09.2004, p. 953-961.

Research output: Contribution to journalArticle

@article{80ce8a35c2184751aa4b58f86bbe067c,
title = "Advanced statistics: The propensity score - A method for estimating treatment effect in observational research",
abstract = "Observational studies assessing the effect of a particular treatment or exposure may be subject to bias, which can be difficult to eliminate using standard analytic techniques. Multivariable models are commonly used in observational research to assess the relationship between a certain exposure or treatment and an outcome, while adjusting for important variables necessary to ensure comparability between the groups. Large differences in the observed covariates between two study groups may exist in observational studies in which the investigator has no control over who was allocated to each treatment group, and these differences may lead to biased estimates of treatment effect. When there are large differences in important prognostic characteristics between the treatment groups, adjusting for these differences with conventional multivariable techniques may not adequately balance the groups, and the remaining bias may limit valid causal inference. Use of a propensity score, described as a conditional probability that a subject will be {"}treated{"} based on an observed group of covariates, may better adjust covariates between the groups and reduce bias. The purpose of this article is to describe the use of propensity scores to adjust for bias when estimating treatment effects in observational research and to compare use of this technique with conventional multivariable regression. The authors present three methods for integrating propensity scores into observational analyses using a database collected on head-injured trauma patients. The article details the methods for creating a propensity score, analyzing data with the score, and explores differences between propensity score methods and conventional multivariable methods, including potential benefits and limitations. Graphical representations of the analyses are provided as well.",
keywords = "bias, propensity score, transfer, trauma",
author = "Craig Newgard and Hedges, {Jerris R.} and Melanie Arthur and Richard Mullins",
year = "2004",
month = "9",
doi = "10.1197/j.aem.2004.02.530",
language = "English (US)",
volume = "11",
pages = "953--961",
journal = "Academic Emergency Medicine",
issn = "1069-6563",
publisher = "Wiley-Blackwell",
number = "9",

}

TY - JOUR

T1 - Advanced statistics

T2 - The propensity score - A method for estimating treatment effect in observational research

AU - Newgard, Craig

AU - Hedges, Jerris R.

AU - Arthur, Melanie

AU - Mullins, Richard

PY - 2004/9

Y1 - 2004/9

N2 - Observational studies assessing the effect of a particular treatment or exposure may be subject to bias, which can be difficult to eliminate using standard analytic techniques. Multivariable models are commonly used in observational research to assess the relationship between a certain exposure or treatment and an outcome, while adjusting for important variables necessary to ensure comparability between the groups. Large differences in the observed covariates between two study groups may exist in observational studies in which the investigator has no control over who was allocated to each treatment group, and these differences may lead to biased estimates of treatment effect. When there are large differences in important prognostic characteristics between the treatment groups, adjusting for these differences with conventional multivariable techniques may not adequately balance the groups, and the remaining bias may limit valid causal inference. Use of a propensity score, described as a conditional probability that a subject will be "treated" based on an observed group of covariates, may better adjust covariates between the groups and reduce bias. The purpose of this article is to describe the use of propensity scores to adjust for bias when estimating treatment effects in observational research and to compare use of this technique with conventional multivariable regression. The authors present three methods for integrating propensity scores into observational analyses using a database collected on head-injured trauma patients. The article details the methods for creating a propensity score, analyzing data with the score, and explores differences between propensity score methods and conventional multivariable methods, including potential benefits and limitations. Graphical representations of the analyses are provided as well.

AB - Observational studies assessing the effect of a particular treatment or exposure may be subject to bias, which can be difficult to eliminate using standard analytic techniques. Multivariable models are commonly used in observational research to assess the relationship between a certain exposure or treatment and an outcome, while adjusting for important variables necessary to ensure comparability between the groups. Large differences in the observed covariates between two study groups may exist in observational studies in which the investigator has no control over who was allocated to each treatment group, and these differences may lead to biased estimates of treatment effect. When there are large differences in important prognostic characteristics between the treatment groups, adjusting for these differences with conventional multivariable techniques may not adequately balance the groups, and the remaining bias may limit valid causal inference. Use of a propensity score, described as a conditional probability that a subject will be "treated" based on an observed group of covariates, may better adjust covariates between the groups and reduce bias. The purpose of this article is to describe the use of propensity scores to adjust for bias when estimating treatment effects in observational research and to compare use of this technique with conventional multivariable regression. The authors present three methods for integrating propensity scores into observational analyses using a database collected on head-injured trauma patients. The article details the methods for creating a propensity score, analyzing data with the score, and explores differences between propensity score methods and conventional multivariable methods, including potential benefits and limitations. Graphical representations of the analyses are provided as well.

KW - bias

KW - propensity score

KW - transfer

KW - trauma

UR - http://www.scopus.com/inward/record.url?scp=4344703837&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=4344703837&partnerID=8YFLogxK

U2 - 10.1197/j.aem.2004.02.530

DO - 10.1197/j.aem.2004.02.530

M3 - Article

C2 - 15347546

AN - SCOPUS:4344703837

VL - 11

SP - 953

EP - 961

JO - Academic Emergency Medicine

JF - Academic Emergency Medicine

SN - 1069-6563

IS - 9

ER -