Skip to main content
MMedVellum
MCQsExamsAtlas
DashboardPricing
MMedVellum

The exam atlas that feels like a flagship product — evidence-graded topics and exam tools for MBBS and fellowship preparation. Built to scale to fifty specialties. Educational content only — not medical advice.

llms.txt·psychiatry LLM catalog · sitemap

Atlas

  • Specialty atlas
  • MBBS / Core medicine
  • Dermatology
  • ICU Fellowship (CICM)
  • Anaesthesia
  • Emergency Medicine
  • Psychiatry Fellowship

Study & account

  • MCQ practice
  • Practice alias
  • Exam tools
  • Dashboard
  • Pricing
  • Sign in

© 2026 MedVellum. For education only — not a substitute for clinical judgement.

Clinical Atlas Prestige · Evidence-first

Psych VivasFoundations — biostatistics for psychiatry exams

Psych Vivas · Foundations — biostatistics for psychiatry exams

Biostatistics — structured clinical viva

Fellowship viva covering NNT, p-values, CI, HR, power, and diagnostic predictive values in psychiatry.

clinical
On this page & tools

Target exams

FRANZCPMRCPsychABPNMD-DNB

Target exams

FRANZCPMRCPsychABPNMD-DNB
Prompt
You are in a FRANZCP/MRCPsych-style viva. The examiner shows a one-page abstract of a multi-centre double-blind RCT of a new antidepressant versus placebo (N=320). Response at 12 weeks: 50% drug vs 35% placebo, p=0.008. Press release claims a '43% relative risk reduction in non-response'. Secondary time-to-relapse in responders over 24 weeks: HR 0.72 (95% CI 0.48 to 1.08). A companion paper reports a new blood biomarker for depression with Sn 0.88, Sp 0.85 in a tertiary mood clinic. Be prepared to calculate NNT, critique relative framing, define p and power, interpret the HR CI, and recompute predictive values conceptually for community prevalence.

Interpretation

Reveal interpretation

NNT. Absolute benefit for response = 0.50 − 0.35 = 0.15 → NNT = 1/0.15 ≈ 7 patients treated for 12 weeks for one extra responder. Prefer this language to relative slogans.[1]

Relative framing. Non-response rates are 50% vs 65%; RRR of non-response = (0.65 − 0.50)/0.65 ≈ 23%, not 43%. The press line may be mixing relative increase in response (0.15/0.35 ≈ 43%) with "risk reduction" wording — demand absolute rates.[1]

p-value. p = 0.008 is compatibility with H0 under the model, not P(drug useless) and not clinical importance by itself.[2]

HR CI. HR 0.72 with CI 0.48–1.08 includes 1 → not conventionally significant; possible benefit remains but so does null — do not claim proven relapse prevention from this secondary alone; absence of significance is not proof of no effect if underpowered.[3][4][6]

Biomarker. Sn/Sp look good in a high-prevalence mood clinic; PPV will fall in low-prevalence community screening — recompute with Bayes or 2×2 at local base rate before adoption.[5]

Key points

Absolute first

Always convert response rates to ARR and NNT with time horizon.

CI for ratios

If 95% CI for HR includes 1, conventional significance fails — read width, not spin.

Base rates

Sn/Sp travel better than PPV across settings.
[1] [4] [5]

References

  1. [1]Cook RJ, Sackett DL The number needed to treat: a clinically useful measure of treatment effect BMJ, 1995.PMID 7873954
  2. [2]Greenland S, Senn SJ, Rothman KJ, et al. Statistical tests, P values, confidence intervals, and power: a guide to misinterpretations Eur J Epidemiol, 2016.PMID 27209009
  3. [3]Altman DG, Bland JM Absence of evidence is not evidence of absence BMJ, 1995.PMID 7647644
  4. [4]Spruance SL, Reid JE, Grace M, Samore M Hazard ratio in clinical trials Antimicrob Agents Chemother, 2004.PMID 15273082
  5. [5]Altman DG, Bland JM Diagnostic tests 2: Predictive values BMJ, 1994.PMID 8038641
  6. [6]Gardner MJ, Altman DG Confidence intervals rather than P values: estimation rather than hypothesis testing Br Med J (Clin Res Ed), 1986.PMID 3082422