So sánh phương pháp

	Nghiên cứu dịch tễ học cắt ngang điều chỉnh theo nguy cơ	Mô hình đa cấp
Lĩnh vực	Dịch tễ học	Thống kê nghiên cứu
Họ	Process / pipeline	Process / pipeline
Năm ra đời	1990s (risk-adjustment integration); cross-sectional design foundational since mid-20th century	1992
Người khởi xướng	Rooted in classical cross-sectional epidemiology (Doll, Hill, Lilienfeld); risk-adjustment formalization attributed to Lisa Iezzoni and colleagues in health outcomes research (1990s)	Anthony Bryk and Stephen Raudenbush
Loại	Observational epidemiological design with statistical adjustment	Method
Công trình gốc	Kelsey, J. L., Whittemore, A. S., Evans, A. S., & Thompson, W. D. (1996). Methods in Observational Epidemiology (2nd ed.). Oxford University Press. ISBN: 978-0195083385	Bryk, A. S., & Raudenbush, S. W. (1992). Hierarchical Linear Models: Applications and Data Analysis Methods. SAGE Publications.
Tên gọi khác	risk-adjusted cross-sectional survey, case-mix adjusted cross-sectional study, standardized cross-sectional analysis, adjusted prevalence study	HLM, mixed-effects models, random effects models, MLM
Liên quan	4	3
Tóm tắt	A risk-adjusted cross-sectional epidemiological study measures the prevalence of health outcomes or exposures in a defined population at a single point in time, then applies statistical risk-adjustment methods — such as regression standardization, direct or indirect standardization, or propensity scoring — to remove the distorting influence of differences in patient case-mix across comparison groups. The approach is widely used in health services research, comparative effectiveness, and clinical quality assessment.	Multilevel modeling (also called hierarchical linear modeling, mixed-effects modeling) is a statistical framework for analyzing data organized in nested or clustered structures—students within schools, patients within hospitals, repeated measures within individuals. Developed by Bryk and Raudenbush (1992), it accounts for dependency among observations and partitions variance into levels (within-cluster and between-cluster), enabling valid inference and revealing context effects. Essential in education, medicine, organizational research, and any field where data have natural hierarchies.