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

Using classification tree analysis to generate propensity score weights.

Ariel Linden1,2, Paul R Yarnold3

  • 1Linden Consulting Group, LLC, Ann Arbor, MI, USA.

Journal of Evaluation in Clinical Practice
|April 4, 2017
PubMed
Summary
This summary is machine-generated.

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

Critical threshold target attainment rates for tazobactam combined with piperacillin among patients admitted to the ICU with hospital-acquired pneumonia.

Antimicrobial agents and chemotherapy·2025
Same author

Pharmacokinetic-pharmacodynamic target attainment with continuous infusion piperacillin in patients admitted to the ICU with hospital-acquired pneumonia.

Antimicrobial agents and chemotherapy·2025
Same author

Individual target pharmacokinetic/pharmacodynamic attainment rates among cefepime-treated patients admitted to the ICU with hospital-acquired pneumonia with and without ECMO.

Antimicrobial agents and chemotherapy·2025
Same author

Individual meropenem epithelial lining fluid and plasma PK/PD target attainment.

Antimicrobial agents and chemotherapy·2023
Same author

Iohexol-measured glomerular filtration rate and urinary biomarker changes between vancomycin and vancomycin plus piperacillin-tazobactam in a translational rat model.

bioRxiv : the preprint server for biology·2023
Same author

Machine Learning To Stratify Methicillin-Resistant Staphylococcus aureus Risk among Hospitalized Patients with Community-Acquired Pneumonia.

Antimicrobial agents and chemotherapy·2022

Classification Tree Analysis (CTA) offers a robust method for generating propensity scores (PS) in non-randomized studies, improving model accuracy and interpretability over traditional logistic regression.

Area of Science:

  • Epidemiology
  • Biostatistics
  • Machine Learning

Background:

  • Propensity scores (PS) are crucial for estimating treatment effects in non-randomized studies.
  • Conventional logistic regression for PS modeling has limitations.
  • Machine learning offers potential improvements for PS modeling.

Purpose of the Study:

  • Introduce Classification Tree Analysis (CTA) as a novel method for propensity score modeling.
  • Compare CTA with logistic regression and boosted regression for PS estimation.
  • Evaluate covariate balance, model accuracy, and treatment effect estimates.

Main Methods:

  • Empirical data used to identify statistically valid CTA PS models.
  • CTA PS weights applied to outcomes analyses.
Keywords:
causal inferenceclassification tree analysismachine learningpropensity score

Related Experiment Videos

  • Comparison with logistic regression and boosted regression using standardized differences, predictive accuracy, and median regression.

    • Main Results:

    • CTA demonstrated the greatest predictive accuracy among the models.
    • While some covariates remained imbalanced across models, treatment effect estimates were consistent.
    • Main-effects logistic regression showed the lowest average standardized difference.

    Conclusions:

    • Standardized differences in means are inappropriate for assessing covariate balance with machine learning algorithms that stratify samples.
    • CTA identifies all statistically valid PS models, increasing the likelihood of correctly specifying the PS model.
    • CTA should be considered as an alternative approach for propensity score modeling.