方法对比

	Propensity Score Methods in Criminology	Criminal Career Paradigm
领域	Criminology	Criminology
方法族	Process / pipeline	Process / pipeline
起源年份	1983	1986
提出者	Paul Rosenbaum & Donald Rubin (method); Apel & Sweeten (criminological application)	Alfred Blumstein, Jacqueline Cohen, Jeffrey Roth & Christy Visher
类型	Observational causal-inference technique applied to crime and justice interventions	Conceptual framework for decomposing offending over the life course
开创性文献	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.	Blumstein, A., Cohen, J., Roth, J. A., & Visher, C. A. (Eds.). (1986). Criminal Careers and 'Career Criminals' (Vols. 1–2). National Academy Press. ISBN: 9780309036887
别名	Propensity Score Analysis in Crime and Justice Research, Criminological Propensity Score Matching, Observational Causal Inference in Criminology, Propensity Score Adjustment for Justice Interventions	Criminal Careers Framework, Career Criminal Paradigm, Offending Career Approach, Blumstein Criminal Career Model
相关	4	4
摘要	Propensity score methods estimate the causal effect of a criminal-justice treatment — such as incarceration, gang membership, a diversion program, or arrest — from observational data, where random assignment is impossible. Building on Rosenbaum and Rubin's 1983 framework and adapted to crime research by Apel, Sweeten, and others, the approach summarizes many confounders into a single probability of treatment, then matches, weights, or stratifies on it to approximate a randomized comparison. This page covers the criminological application; for the general estimators see propensity-score-matching and propensity-score-weighting.	The criminal career paradigm is a framework for studying offending as a longitudinal sequence in an individual's life rather than as undifferentiated aggregate crime. Codified by Blumstein, Cohen, Roth, and Visher in the 1986 National Academy of Sciences report, it decomposes crime into distinct dimensions — whether someone offends (participation), how often active offenders offend (frequency, λ), and the onset, seriousness, and duration of the career — each potentially with different causes.