Propensity score matching

Last revised by Rohit Sharma on 15 Jan 2023

Citation, DOI, disclosures and article data

Citation:

Moore C, Sharma R, Murphy A, Propensity score matching. Reference article, Radiopaedia.org (Accessed on 20 Apr 2024) https://doi.org/10.53347/rID-159853

DOI:

https://doi.org/10.53347/rID-159853

Permalink:

https://radiopaedia.org/articles/159853

rID:

159853

Article created:

8 Jan 2023, Candace Makeda Moore

Disclosures:

At the time the article was created Candace Makeda Moore had no financial relationships to ineligible companies to disclose.

View Candace Makeda Moore's current disclosures

Last revised:

15 Jan 2023, Rohit Sharma ◉

Disclosures:

At the time the article was last revised Rohit Sharma had no financial relationships to ineligible companies to disclose.

View Rohit Sharma's current disclosures

Revisions:

3 times, by 3 contributors - see full revision history and disclosures

Propensity score matching is a statistical technique used with observational data to elucidate the effects of a treatment or intervention by accounting for the covariates which accompany receiving the particular treatments or interventions studied. By accounting for covariates the technique often reduces the influence of confounding variables in analysis. This technique is particularly useful when a randomized control trial is unethical or unfeasible.

History and etymology

Propensity score matching has been in use since the 1980s when it was introduced by Paul Rosenbaum and Donald Rubin ¹. The technique has been used in radiology research over the last decade and is increasingly used in clinical research in general ².