Essentials of Biostatistics and Public Health Practice Questions and Answers

Distinguish between the two main types of epidemiology studies. What are the inferences of each? (1) Observational studies (sometimes called descriptive or associational studies, nonrandomized, or historical studies. Observational studies can be used to alert the medical community, they can be used to generate hypotheses, and they can be used to assess specific associations. Inferences limited to descriptions and associations; with carefully designed analysis can make stronger inferences (statistical adjustment). (2) Randomized studies (sometimes called analytic or experimental studies) can be used to test hypotheses or to evaluate the effect of an intervention (e.g., a behavioral or pharmacologic intervention). Inferences are cause-and-effect. Case-control study: design Observational & retrospective; compares a group of people w/ disease to a group without the disease; looks for prior exposure or risk factor; asks, "what happened?" Case-control study: measures, examples, advantages & disadvantages. Measures Odds Ratio; "pts w/ COPD had higher odds of a history of smoking than those without COPD" Advantages: Cost and time efficient for rare outcomes, Best for diseases with long latency. Disadvantages: Need careful selection of cases and controls, Bias: - Selection bias - select cases or controls and some drop out - leaving groups not comparable - Observation bias - knowledge of disease might influence reporting of exposure (overreporting among cases) - Recall bias - retrospective (long term) Cohort study: design Observational & prospective; compares a group with a given exposure or risk factor to a group that has had no exposure; looks to see if exposure incr. the likelihood of disease; asks, "what is happening over time?" Cohort study: measures, examples, advantages & disadvantages. Measures Relative Risk Example: smokers had a higher risk of developing COPD than did nonsmokers Advantages: can access temporal relationships Disadvantages: need large numbers for rare outcomes, confounding