Post 4: Case-Control Study Design

These studies are based on the observation of naturally occurring exposures and test hypotheses that look to answer questions that may have risen from population based studies.  They are often called retrospective studies because researchers start with an end point and work backwards to determine what might have caused the outcome and allow multiple risk factors to be considered¹.  For example, researchers could take two groups of participants, one who have been diagnosed with osteoporosis (cases) and those who haven’t (controls).  Researchers could then work backwards and survey the two groups about their earlier health behaviours to determine what might have caused the disease to develop or not.  They may explore issues such as calcium intake or dietary intake to compare differences in risk factors or exposures that emerge in each group².  

Image 3: Schematic diagram of Case-Control study design

	While the main problem with case-control studies is that they are susceptible to recall bias and confounding, that is a third, difficult to predict, variable. However they are useful in measuring the strength of the association between an exposure and the outcome, identify possible predictors of outcome and yield an odds ratio which usually then approximates the relative risk.

---

1   Lewallen S Courtright P.  Epidemiology in Practice: Case-Control Studies. Comm Eye Hlth. 1998; 11(28):57-58

2   Himmelfarb Health Sciences Library.  Study Design 101: Case Control Study, [cited May 4 2015] https://himmelfarb.gwu.edu/tutorials/studydesign101/casecontrols. html