TOG Review (RCOG Journal)

MRCOG Part 2

Teaching and Research

A practical introduction to medical statistics

Key Statistics

  • P<0.05 — Conventional significance threshold
  • ±1.96×SE — 95% CI = effect size ± this
  • 80% — Typical target power (1−β)

Don't-miss facts

  1. A statistically flawed study is an ethically flawed study

  2. 95% CI = effect size ± 1.96 × SE; SE = SD/√n (uncertainty in estimate, not spread of data)

  3. P<0.05 conventional threshold – P-value is the probability of the observed (or more extreme) result assuming H0 true, NOT the probability H0 is true

  4. Type I error = α (reject true H0); Type II error = β (accept false H0); Power = 1−β, usually target 80%

  5. Statistical significance ≠ clinical importance – always ask about effect size, not just P-value

  6. OR ≈ RR only when event prevalence <10%; OR overestimates RR at higher prevalence

  7. Fisher's exact test for small samples/single-digit cell counts; chi-squared otherwise

  8. Worked example: smoking & low birthweight – RR 1.61 (95% CI 1.06–2.44), OR 2.02 (95% CI 1.08–3.77)

Parametric vs non-parametric (2 independent groups)

Parametric: t test (ratio/interval, normal) → effect size + CI + P

Non-parametric: Mann–Whitney U/Wilcoxon rank-sum (ordinal/non-normal) → P-value only

Abbreviation Key

  • SD — standard deviation
  • ANCOVA — analysis of covariance
  • SE/SEM — standard error (of the mean)
  • MWU/WRS — Mann–Whitney U / Wilcoxon rank-sum test
  • CI — confidence interval
  • IQR — interquartile range
  • RCT — randomised controlled trial
  • α — probability of a type I error
  • OR — odds ratio
  • β — probability of a type II error
  • RR — risk ratio (relative risk)

Source: Scally AJ. A practical introduction to medical statistics. The Obstetrician & Gynaecologist 2014;16:121–8. doi:10.1111/tog.12081

MRCOG AI is an independent educational tool. It is not affiliated with, endorsed by, or connected to the Royal College of Obstetricians and Gynaecologists (RCOG).

Included with a Pass Package

  • Audio overview of this guideline
  • Practice questions drawn from it
  • AI tutor answers grounded in its text
  • Your own annotations
Start free