How to set up comparisons

Last Update: March 15, 2011

To identify causes of disease and quantify how much they contribute (i.e., their effects), we need to compare counts: we need to compare the frequency of coronary heart disease between people with different characteristics to know how much the characteristic contributes to the frequency of the disease. There are several ways to set up such comparisons: different study designs which lead to different measures of effect to summarize the count comparisons. The measures of effect that are used widely in epidemiology are the risk ratio, risk difference, odds ratio and number needed to treat. Study designs consist of cohort studies, case-control studies, and of cross sectional, and ecologic comparisons.

Background publications

Morabia A (2004) Epidemiology: An epistemological perspective. In History of epidemiological methods and concepts , Morabia A (ed) pp 1-126. Birkhäuser: Basel , sections 3.1-3.3, 3.5-3.6, 3.10-3.12,

Doll R (2004) Cohort studies: history of the method. In History of Epidemiologic Methods and Concepts , Morabia A (ed) Birkhäuser: Basel, pp 243-274. Older version in SPM, part 1 and part 2.

Paneth N, Susser E, Susser M (2004) Origin and early development of the case-control study. In History of Epidemiologic Methods and Concepts , Morabia A (ed) Birkhäuser: Basel, pp 291-312. Older version in SPM, part 1 and part 2.

Key papers