手法を比較

	多変量縦断研究	構造方程式モデリング
分野	研究デザイン	研究統計
系統	Process / pipeline	Process / pipeline
提唱年	1970s–1980s (formalized in behavioral sciences literature)	1921
提唱者	Nesselroade, Baltes, and the developmental/behavioral sciences tradition	Sewall Wright
種類	Quantitative observational research design	Method
原典	Nesselroade, J. R., & Baltes, P. B. (Eds.). (1979). Longitudinal Research in the Study of Behavior and Development. Academic Press. ISBN: 978-0125154505	Jöreskog, K. G., & Sörbom, D. (1973). LISREL: A general computer program for estimating a linear structural equation system. Research Bulletin 73-5. University of Stockholm.
別名	longitudinal multivariate design, MLR, multivariate panel study, multivariate repeated-measures design	SEM, path analysis, latent variable modeling, causal modeling
関連	4	3
概要	Multivariate longitudinal research is a quantitative observational design that follows the same units — individuals, groups, or organizations — across two or more time points while measuring several outcome and predictor variables simultaneously. By combining the temporal dimension of longitudinal tracking with multivariate statistical analysis, it allows researchers to examine how a system of variables co-evolves, how early measures predict later outcomes across multiple domains, and whether relationships among variables are stable or change over time.	Structural equation modeling (SEM) is a comprehensive statistical framework combining path analysis (Sewall Wright, 1921) and confirmatory factor analysis to test complex causal models linking observed and latent variables. Formalized by Jöreskog (1973) with LISREL software, SEM enables simultaneous estimation of measurement relationships (how variables measure latent constructs) and structural relationships (how constructs influence outcomes), making it powerful for theory testing in psychology, epidemiology, organizational research, and health sciences where complex mediation, moderation, and latent processes require integrated analysis.