Research Questions, Objectives, and Hypotheses
A testable statement predicting a relationship between two variables (e.g., exposure and disease)
What is a research hypothesis?
Non-randomized study that follows subjects forward in time
What is a prospective cohort study?
Primary method/tool used to control for confounding and selection bias
What is randomization?
Derives from generalizability of study results
What is external validity?
Checklist used for assessing the quality of a cohort study
What is STROBE?
Framework (anagram) used to guide a research question
What is PICOT(S) (Population, Intervention, Outcome, Time, Setting)?
Design that involves a series of observations before and after the treatment
What is interrupted-time-series?
Unit of randomization is a group of subjects
What is a cluster randomized trial?
Blinding (Masking) is used to control for this bias
What is observation bias? OR What is performance bias? OR What is detection bias? (all acceptable)
Discrete variable with only two values
What are dichotomous outcomes?
The two data types for numerical outcomes
What are discrete (counts) and continuous?
Disease prevalence rather than incidence is assessed in this kind of study.
What is a cross-sectional study?
Subjects analyzed based on group to which they were originally assigned
What is intention-to-treat analysis?
Distortion of the estimated effect of an exposure on an outcome due to the presence of a common cause of exposure and outcome
What is confounding?
Randomly selected subset of the population
What is a random sample?
Drugs, devices, or procedures are all examples of what in a clinical trial?
What is an intervention?
What is a key assumption in the difference-in-difference design?
What is the parallel trends assumption?
What is stratification OR What is blocking OR what is blocked stratification? (all acceptable)
Bias that can occur if subjects who are less healthy drop out of study
What is attrition bias?
Extent to which repeated measurements produce the same result
What is reliability?
The study of the distribution of health-related states and events in specified populations
What is epidemiology?
Method to control for confounding during the analysis phase
What is regression?
What is a cross-over trial?
Name three types of reporting biases
What is publication bias? What is selective outcome reporting bias? What is language bias? What is citation bias? etc.
A method to control for confounding during the study design phase for an observational study
What is matching?