Σύγκριση μεθόδων

	Propensity Score Matching in Education	Αντιστοίχιση Βαθμολογίας Προδιάθεσης
Πεδίο	Education	Ερευνητική Στατιστική
Οικογένεια	Process / pipeline	Process / pipeline
Έτος προέλευσης	1983	1983
Δημιουργός	Rosenbaum & Rubin (method); educational application widespread (Stuart and others)	Paul Rosenbaum and Donald Rubin
Τύπος	Observational causal inference by matching treated and untreated units on treatment probability	Method
Θεμελιώδης πηγή	Rosenbaum, P. R., & Rubin, D. B. (1983). The central role of the propensity score in observational studies for causal effects. Biometrika, 70(1), 41–55.	Rosenbaum, P. R., & Rubin, D. B. (1983). The central role of the propensity score in observational studies for causal effects. Biometrika, 70(1), 41–55.
Εναλλακτικές ονομασίες	Educational Propensity Score Matching, PSM in Education, Propensity Matching for School Effects, Observational Causal Matching	PSM, propensity score weighting, covariate balance
Συναφείς	4	3
Σύνοψη	Propensity score matching estimates the causal effect of an educational treatment from observational data by pairing treated students, schools, or teachers with comparison units that had the same probability of receiving the treatment given their observed characteristics. Introduced by Rosenbaum and Rubin, it collapses many confounding variables into a single score and matches on it, approximating the balance a randomized experiment would create. In education — where randomizing program participation, retention, or school choice is often impossible — it is a widely used quasi-experimental tool.	Propensity score matching (PSM) is a method for reducing confounding bias in observational studies by balancing baseline characteristics between treatment groups, simulating randomization. Developed by Rosenbaum and Rubin (1983), it estimates the probability of receiving treatment given observed covariates, then matches or weights treated and control individuals with similar treatment probabilities. Widely used in medicine, epidemiology, and policy evaluation when randomized trials are infeasible or unethical, enabling estimation of treatment effects while controlling for selection bias.