Research & Evidence-Based Medicine

20 learning units • 100 chapter sections • 200 explained questions. Build a question, judge the evidence and connect the answer with the person receiving care.

Original RAHBAR study material for the Year 3 learning pathway. Educational examples support supervised learning; institutional research and clinical requirements still apply. References & further reading ↓

MODULE 08 / 20

Hypothesis Tests, P Values & Power

Interpret statistical evidence alongside effect size, uncertainty and the decisions made before analysis.

Choose an answer and check it immediately. Change your choice to try again. This is a self-study exercise; results are not saved.

Question 01. What does p = 0.03 mean under a valid test model? A. Such or more incompatible results have probability 0.03 if the null holdsB. The null has a 3% probability of being trueC. There is a 97% probability the treatment worksD. The treatment improves outcomes by 3%

Question 02. Rejecting a true null hypothesis is which error? A. Type IB. Type IIC. Measurement reliabilityD. Allocation concealment

Question 03. What is statistical power? A. One minus the type II error probability for a specified alternativeB. The probability the null is trueC. The observed treatment effectD. The proportion lost to follow-up

Question 04. Can an extremely small p value accompany a clinically trivial effect? A. Yes, especially with a large sampleB. No, significance guarantees large benefitC. Only if the data are categoricalD. No, p values equal effect size

Question 05. What does a non-significant superiority trial establish by itself? A. Equivalence of treatmentsB. Insufficient evidence to reject its null at the chosen thresholdC. Absence of any possible harmD. A clinically important benefit

Question 06. Why prespecify a primary outcome? A. To guarantee significanceB. To eliminate all random errorC. To avoid defining follow-upD. To reduce selective emphasis after seeing results

Question 07. What is a consequence of many unadjusted significance tests? A. Guaranteed removal of confoundingB. Automatic improvement in external validityC. More opportunities for false-positive findingsD. Every interval becomes a prediction interval

Question 08. Which information is needed for a defensible sample-size calculation? A. Only the preferred study conclusionB. Only the journal word limitC. Target effect and assumptions about variation or event ratesD. Only the number of available authors

Question 09. What is usually more informative than observed post hoc power after a study? A. The effect estimate and confidence intervalB. The colour of the graphC. The number of references aloneD. The investigator’s confidence alone

Question 10. What is required for a convincing non-inferiority claim? A. A justified prespecified margin and suitable design and analysisB. Any p value above 0.05 in a superiority testC. Removing all participants with poor outcomesD. Reporting only a favourable subgroup

0 / 10 answeredReady for assessment →

References & Further Reading

Use the full methods and relevant chapters when appraising a paper. These sources support further study; the examples and questions above are original teaching exercises.

Reference review: 25 September 2026. Consult current institutional guidance for project approval and clinical decisions.