Skip to Main Content


Types of Clinical Studies & Trials

  • Case control study: Compares a group of patients with a disease (“cases”) to a group of patients who do not have the disease (“controls”). Looks backward in time (i.e., a retrospective study) to determine if there is a difference in exposure to a potential risk factor between cases and controls. Generates an odds ratio (OR). If an outcome is rare, the OR will be close to the risk ratio (RR) (“the rare disease assumption”).

  • Cohort study: Compares a cohort of patients who were exposed to a potential risk factor with a cohort of patients who were not exposed. May be prospective (follow the two cohorts and compare disease incidence) or retrospective (review records of disease incidence for each cohort).

  • Cross-sectional study: “Prevalence study”: A snapshot in time with both exposure and outcome measured simultaneously; may establish association but not causation.

  • Clinical trial types: Sample and control group

    • - Parallel design: Randomizes one treatment to one group and a different treatment to another group (e.g., treatment vs. placebo)

    • - Factorial design: Randomizes to different interventions with additional study of two or more variables (e.g., treatment vs. placebo, and in each group also studying one heart rate goal vs. another)

    • - Cross-over design: One group randomized to treatment A and another group randomized to treatment B, the treatment received are reversed in the second half of the study

  • Clinical trial phases:

    • - Phase I: A small number of healthy volunteer participants (or sometimes volunteer participants with the disease of interest, depending on the context), aiming to determine the highest dose of the drug humans can take without serious side effects

    • - Phase II: A new drug is given to a small number of volunteer participants with the disease of interest, aiming to determine the preliminary safety and efficacy of the new drug

    • - Phase III: A new drug is given to a larger number of volunteer participants with the disease of interest. Participants are typically randomized to receive the new drug/treatment vs. the standard or care or a placebo. The US FDA typically requires a phase III trial before approving a new medication

    • - Phase IV: Post-marketing surveillance



  • Selection bias: Bias in selecting the study group. Subtypes: Attrition bias (participants lost to follow-up), non-response bias (can occur with surveys when low response rate), selection bias

Study execution

  • Recall bias: Inaccurate recall of past events by patients; common in case-control studies

  • Observer bias: Observer may be influenced by prior knowledge or details of the study that affect the results; mitigated by blinding

  • Measurement bias: Poor data collection, inaccurate results

Data/result interpretation

  • Confounding bias: At least part of the exposure-disease relationship can be explained by another variable

  • Susceptibility ...

Pop-up div Successfully Displayed

This div only appears when the trigger link is hovered over. Otherwise it is hidden from view.