(11.1) Study Questions
(A) Experimental studies have investigator controlled interventions ("treatments"). Observational studies do
not.
(B) Double-blinded = person taking measurements and patients do not know which treatment they are
receiving. Randomized = the treatment was allocated based on chance. Controlled = there are at least two
treatments; one of the treatments may be placebo ("placebo controlled trial"), but not necessarily.
(C) It is a way of viewing information; a way of learning from data.
(D) Observed changes and differences may have occurred over time had no intervention taken place
("confounding by time").
(E) In intention-to-treat analysis (analyze as randomized), case ascertainments continue regardless of whether
the participants were compliant. "Efficacy analysis" considers only patients who were compliant. The two main
advantages of intention-to-treat analysis are (1) it reflects the way the treatment will perform in the population
/ effectiveness analysis and (2) it guards against investigator bias. On the other hand, it may not accurately
reflect the physiological effects of the treatment.
(F) (1) The research question must be fully formed and clearly stated. (2) The project and its measurements
are feasible. (3) Every facet of the protocol must be carefully considered and documented. (4) Research has
consequences.
(G) Longitudinal samples entail follow-up of individuals over time.
(H) It ensures (encourages that?) the two groups will be balanced with respect to known and unknown factors
that might influence the outcome.
(I) Write a study question, not a research question.