方法对比

	基于元回归的元分析	系统性文献综述
领域	科学计量学	科学计量学
方法族	Process / pipeline	Process / pipeline
起源年份	1993–1999	1993 (Cochrane Collaboration); 2004 (Kitchenham SLR guidelines)
提出者	Stephen G. Thompson & Simon J. Sharp (systematic framework); earlier work by Berlin, Longnecker & Greenland (1993)	Archie Cochrane (conceptual foundation); formalized by the Cochrane Collaboration (1993) and Barbara Kitchenham in software engineering (2004)
类型	Quantitative evidence synthesis with covariate modeling	Evidence synthesis methodology
开创性文献	Thompson, S. G., & Sharp, S. J. (1999). Explaining heterogeneity in meta-analysis: a comparison of methods. Statistics in Medicine, 18(20), 2693–2708.	Kitchenham, B. (2004). Procedures for Performing Systematic Reviews. Keele University Technical Report TR/SE-0401.
别名	meta-regression, meta-analytic regression, weighted regression meta-analysis, MR-MA	SLR, systematic review, evidence synthesis review, structured literature review
相关	4	5
摘要	Meta-regression-based meta-analysis extends standard meta-analysis by fitting a weighted regression model in which study-level characteristics (moderators) predict observed effect sizes. Rather than simply pooling effects, this approach asks why effects vary across studies — linking heterogeneity in outcomes to differences in population, intervention, design, or measurement features. It is the primary tool for explaining between-study variance in quantitative evidence synthesis.	A systematic literature review (SLR) is a structured, reproducible method for identifying, appraising, and synthesizing all relevant studies on a research question. Unlike a narrative review, it follows an explicit, pre-specified protocol — from database search strings through inclusion criteria to data extraction — so that the process is transparent, auditable, and replicable by other researchers. It is widely used in medicine, education, software engineering, and the social sciences to produce the most comprehensive possible evidence base on a topic.