Full course description
Observational research is aimed at studying the occurrence of phenomena that are “naturally” present in the population or society, and characteristics that are associated with these phenomena. Because experimental (intervention) research is not feasible for many relevant health issues, observational research is often needed to answer these questions. This can concern research on cause and effect aimed at (genetic and environmental) factors influencing the etiology or prognosis of diseases, factors that can explain specific behaviour, or descriptive research. Observational research forms the cornerstone of epidemiological research.
This module elaborates theoretical and practical aspects of observational research. Moreover, quantification of a number of methodological phenomena, such as confounding and effect modification will take place. Students will learn to evaluate various observational designs regarding strengths and weaknesses, depending on the setting where these designs are being applied.
By means of lectures, exercises and skills training sessions attention will be paid to the following aspects: Observational research designs and their advantages and disadvantages: case-control studies, cohort studies, nested case-control and case-cohort designs, correlation study, cross-sectional research; Choosing among designs; Exposure measurement in observational research and potential misclassification; Sources of bias in various designs: selection bias, confounding and information bias. Illustration and quantification of these terms in different designs, and ways to deal with bias; Stratified and matched analyses; Effect modification and statistical analysis procedures; Causal reasoning and causal diagrams; Application of these analysis techniques in different observational research designs; Reporting guidelines for observational research.
Students who register are requested to work on practical assignments regarding statistical analyses using existing datasets, in addition to intensive course participation. The course will be concluded with a written test.
- Principles and practice of observational studies
- Designs for etiologic and prognostic epidemiologic research
- Hybrid designs: Nested case-control studies + case-cohort studies
- Selection bias, information bias (misclassification) and confounding
- Matching, stratified analysis, Mantel-Haenszel testing, standardization
- Evaluation of effect modification (interaction)
- Causal inference, causal diagrams, principles of causal reasoning
- Reporting of observational studies in epidemiology: STROBE
Basic Textbook: Szklo M, Nieto J. Epidemiology Beyond the Basics. Jones and Bartlett Learning, 2014 (third edition). Other literature from scientific journals will be made available through the Reference List in the Student Portal > My Courses