MDM

Question 1

What is a case control study?

Answer 1

Retrospective. Compare cases who have a certain outcome (i.e. lung cancer) with individuals who do not have that outcome (i.e. no lung cancer). The cases are matched to the control group. Then look for certain variables which are more commonly associated with the outcome (i.e. smoking is much more common among lung cancer patients vs non lung cancer patients) Only can study 1 outcome at a time

Question 2

What are the advantages/disadvantages of case control study?

Answer 2

Advantage: Can be used to study outcomes that are rare or have long latency. Less time consuming, less expensive (no follow up required). Cohort study -> need to wait to find individuals with outcome, which can take a long time. Disadvantage: Susceptible to bias since everything is retrospective (i.e. patients may lie). Cannot be used to study prevalence. Also, it may be difficult to study rare exposures.

Question 3

What is a cohort study?

Answer 3

Select population -> divided by exposure -> see what outcome is -> prospective or retrospective -> good for looking at multiple outcomes as well

Question 4

Are cohort studies prospective or retrospective? Case control?

Answer 4

Cohort -> both Case control -> retrospective

Question 5

What is recall bias?

Answer 5

If data collection involves asking participants about their exposure after the outcome has occurred…. the individuals may 1) misremember 2) lie about doing something embarrassing 3) have pre-existing beliefs 4) have died

Question 6

Why might a researcher choose to use an observational study over an RCT?

Answer 6

Researchers might choose to perform an observational study when a randomized controlled study would be unethical, when the length of time between exposure and outcome is very long, or when the outcome is very rare.

Question 7

What are the differences between a cohort study and a case control study?

Answer 7

Cohort study -> cohort chosen and then divided based on exposure. Then outcomes are tracked for each group and results are calculated using risk ratios. Multiple outcomes can be tracked and results reported. Example: study a cohort of people and examine risk related to smoking. Compare risk of heart disease, lung cancer, etc in people from the smoking group and the non smoking group

Case Control: Based on outcome. Control group chosen to match up with the case group. Multiple exposures can be tracked but only one outcome chosen (obviously since you chose the case group based on the outcome). Results reported as odds ratios.

Question 8

What is selection bias?

Answer 8

Selection bias is the bias introduced by the selection of individuals, groups or data for analysis in such a way that proper randomization is not achieved, thereby ensuring that the sample obtained is not representative of the population intended to be analyzed.

Maintains internal validity but compromises external validity (generalizability)