What is the difference between an analytical study and a descriptive study?
An analytical study asks a question about a relationship between variables, while a descriptive study asks a general question about one variable.
What does PICO stand for?
Patient/problem, intervention, comparison, outcome.
What are the 3 questions to ask about a study?
- What is the aim?
- If there is an intervention, is it randomly allocated?
- When were the outcomes determined?
What are the strengths and weaknesses of an RCT?
Strengths: unbiased distribution of confounders, blinding can be done easily, randomization is better for statistical analyses
Weaknesses: expensive in terms of time and money, volunteer bias, ethical problems
What are the strengths and weaknesses of a crossover design?
Strengths: within-subject variability is reduced, blinding can still be done, analyses can assume randomization
Weaknesses: all participants receive no treatment/placebo at one point, washout periods can be long/unknown, can’t be done for permanent treatments
What are some strengths and weaknesses of a cross-sectional design?
Strengths: quick, easy, no ethical issues
Weaknesses: cannot infer causality, recall bias, distribution of confounders is biased, unequal group sizes
What are some strengths and weaknesses of a case-control study?
Strengths: quick, cheap, good for rarer conditions, fewer people are needed
Weaknesses: reliance on recall/records, confounders, selection of control groups is difficult, potential selection and recall biases
What are some strengths and weaknesses of a cohort study?
Strengths: ethically safe, subjects can be matched, can establish timing and directionality of events, eligibility criteria and outcomes can be standardized, easier and cheaper than an RCT.
Weaknesses: controls are difficult to identify, exposure may be linked to a confounder, blinding is difficult, no randomization, large sample sizes and follow-ups are needed for rare diseases.
What is the definition and formula for sensitivity?
The percent of individuals that will test positive out of all the people that have the condition.
True positives / (true positives + false negatives)
What is the definition and formula for specificity?
The percent of people that will test negative out of all the people that do not have the condition.
True negatives / (true negatives + false positives)
What are highly sensitive tests useful for?
Ruling conditions OUT.
What are highly specific tests useful for?
Ruling conditions IN.
What is the difference between a surrogate and a meaningful outcome?
Surrogate outcome: a lab measure or physical sign that is intended to be used as a substitute for a clinically meaningful endpoint
- i.e. lowered BP is a surrogate outcome for lowered CVD risk and prolonged life
Meaningful outcome: a clinically meaningful endpoint that is a direct measure of how the individual feels, functions, and survives
- i.e. a hip replacement has a direct effect on how someone feels via decreased pain and increased ROM
