Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Propensity scores: an introduction and experimental test.

Jason K Luellen1, William R Shadish, M H Clark

  • 1Department of Psychology, University of Memphis, TN 38152-3230, USA. jluellen@memphis.edu

Evaluation Review
|October 26, 2005
PubMed
Summary

Propensity score analysis balances groups in quasi-experiments for accurate treatment effect estimation. This statistical method enhances data analysis by comparing non-equivalent groups using observed covariates.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

The Impact of Sodium Hexametaphosphate Use in Soil Fractionation Protocols on Downstream Mineral Analyses.

ACS omega·2026
Same author

Syringe service program leader and participant perspectives on reasons for opioid-stimulant co-use in the United States.

Drug and alcohol dependence reports·2025
Same author

Understaffed and beleaguered: a national survey of chiefs of police about the post-George Floyd era.

Policing (Bradford, England)·2025
Same author

Beliefs of US chiefs of police about substance use disorder, fentanyl exposure, overdose response, and use of discretion: results from a national survey.

Health & justice·2025
Same author

The effects of message framing on US police chiefs' support for interventions for opioid use disorder: a randomized survey experiment.

Health & justice·2024
Same author

Factors affecting problem-solving court team decisions about medications for opioid use disorder.

Journal of substance use and addiction treatment·2024

Area of Science:

  • Statistics
  • Biostatistics
  • Epidemiology

Background:

  • Quasi-experimental studies often involve non-equivalent groups.
  • Accurate estimation of treatment effects is crucial in these settings.
  • Existing methods may struggle to adequately control for confounding variables.

Purpose of the Study:

  • To introduce propensity score analysis for quasi-experimental data.
  • To demonstrate its application by comparing a quasi-experiment to a randomized experiment.
  • To provide practical guidance and discuss limitations of the approach.

Main Methods:

  • Propensity score analysis is detailed as a statistical technique.
  • Classification tree analysis and bagging for classification trees are presented for propensity score construction.

Related Experiment Videos

  • Ensemble methods are introduced as advanced classification algorithms for computing propensity scores.

    • Main Results:

    • Propensity score analysis can balance observed covariates between non-equivalent groups.
    • This balancing leads to more accurate treatment effect estimates.
    • The study provides a practical example and methodological insights.

    Conclusions:

    • Propensity score analysis is a valuable tool for analyzing quasi-experimental data.
    • Novel methods using classification trees and ensemble methods are introduced for propensity score computation.
    • The approach offers practical advice and acknowledges limitations for researchers.