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 12 / 20

Cohorts, Case-Control Studies & Prognosis

Read longitudinal and outcome-sampled research with attention to time, denominators and follow-up.

Answer all 10 questions, then submit to see your score and explanations. This is a self-study exercise; results are not saved.

Question 01. What should controls in a case-control study represent? A. The source population’s exposure distribution under the sampling schemeB. Only people with no health problems everC. Only the investigators’ relativesD. Only people known to be unexposed

Question 02. What is right censoring? A. The event time beyond the last observation is unknownB. Proof the event will never happenC. Exclusion of every eventD. Assigning all patients the same survival time

Question 03. Ten people contribute two years each at risk. What is the total person-time? A. 5 person-yearsB. 10 person-yearsC. 20 person-yearsD. 2 person-years

Question 04. Why inspect numbers at risk on a survival plot? A. They always equal the original sampleB. Late estimates may depend on few remaining peopleC. They prove censoring is unbiasedD. They replace confidence intervals entirely

Question 05. What does calibration assess in a prediction model? A. Agreement of predicted and observed risksB. Only the ranking of patientsC. Whether all coefficients are positiveD. Whether the model uses a computer

Question 06. What does discrimination assess? A. Agreement of every absolute risk estimateB. Ability to distinguish people with and without the outcomeC. Trial allocation concealmentD. Whether the sample is nationally representative

Question 07. Which statement about a hazard ratio is correct? A. It always equals the five-year risk ratioB. It is always an absolute risk differenceC. It compares instantaneous event rates among those still at riskD. It directly gives NNT without baseline information

Question 08. Why define a common disease stage at entry to a prognosis cohort? A. To guarantee every outcome is identicalB. To eliminate the need for follow-upC. To make the starting point clinically interpretableD. To ensure every patient receives random therapy

Question 09. What threatens standard survival analysis when sick participants disproportionately disappear? A. Guaranteed complete outcome observationB. Better randomisationC. Perfect calibrationD. Informative censoring

Question 10. What is an important next step before using a prediction model in a new hospital? A. Assuming development accuracy transfers unchangedB. External validation and assessment of usefulnessC. Removing all uncertainty estimatesD. Using only the most complex available model

0 / 10 answered

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.