Observational studies

*In observational studies, the investigator identifies subjects as they occur in nature, and observes some response of interest for each subject.

These types of studies can be;

• Prospective: the subject’s explanatory level is identified first, and then the outcome or response of interest is observed.
• Retrospective: subject’s outcomes are observed first, and then the information on any explanatory variable(s) is obtained.

Consider epidemiologic studies to determine the association between cigarette smoking and lung cancer.

• We could identify smokers and nonsmokers (explanatory variable) and determine whether or not they develop lung cancer in some fixed period (response); this would be prospective.
• An alternative approach would be to identify hospital patients with and without lung cancer (response) and then determine whether or not the person had smoked (explanatory variable); this would be retrospective.

The next posts would be about the three major types of observational study designs;
case-control, cohort and cross-sectional