Statistics and Research — Prometric Style Questions, Set 1

What this deck covers

Statistics and Research — Prometric Style Questions, Set 1 in 50 board-style clinical cases with worked explanations. Each case gives you a clinical vignette, four options, the correct answer, and an explanation of why each of the other three is wrong, with the guideline or textbook it follows named on the answer.

Board-style teaching questions for paediatricians and trainees preparing for board, MRCPCH and Prometric examinations. Written from published guidelines and standard paediatric textbooks, with the source named on every answer.

The 50 cases, in order

1. Choosing an average
2. How far from the middle
3. Below the lowest line
4. Same average, different wards
5. Why charts disagree
6. Which test property matters
7. A good test with false alarms
8. Working out the numbers
9. Shifting the probability
10. Moving the cut-off
11. Before starting a programme
12. The clock started early
13. A talk about handwashing
14. Picking the screening test
15. A positive newborn result
16. Studying a rare malformation
17. Finding rare side effects
18. Proving a treatment works
19. A survey taken in one day
20. A third factor in the middle
21. Remembering what happened
22. Children who stopped the drug
23. When blinding is impossible
24. Only the severe cases
25. How many to treat
26. Half of what, exactly
27. Odds or risk
28. Not proven, or disproven
29. What the p value says
30. How many children are needed
31. A tiny difference in height
32. Two studies, same answer
33. More children, same new cases
34. Counting deaths in babies
35. Where to build the hospital
36. Beyond counting deaths
37. Three children, one nursery
38. When to notify a case
39. Measuring quality of care
40. Why incidents happen
41. Reducing diagnostic errors
42. Sugar limits and play areas
43. Which evidence is strongest
44. Reading a forest plot
45. A gap in the funnel
46. A younger child in clinic
47. The protocol says something else
48. Better without treatment
49. Studying a rare exposure
50. Choosing a statistical test

Diagnoses and management options tested

Across the fifty cases you are asked to choose between options such as: The arithmetic mean of all the recorded stays, The mode of the waiting times recorded, The test must be technically faulty in some way, Sensitivity rises and specificity falls, Primordial prevention, A randomised controlled trial of the medication, Prevalence cannot be measured in this type of study, It increases the statistical power of the analysis, Two children, A relative risk below 1 always proves benefit exists, The p value is too small to be believable, Neonatal mortality rate, Close the nursery immediately as a precaution, That the incident reporting system is being misused.

Clinical pearls from this deck

• Look at the shape before choosing the summary. One very long stay can move the mean and leave it describing nobody.
• Learn 68, 95 and 99.7 once. It explains the second centile on every growth chart you will ever plot.
• Below the bottom line is not a measurement. A score of minus three or minus five tells you which child is in trouble, and the chart cannot.
• A mean without a spread is half a result. The two wards here are indistinguishable on paper and completely different to sit in.
• The centile describes the chart as much as the child. Switching charts mid-follow-up invents a growth problem that was never there.
• Ask which error hurts more. A missed case or a false alarm decides which property you buy, and you cannot maximise both.

Work through the deck once for recognition, then again a week later to test yourself — each question gives the answer and explains why every other option fails.

More from this system: all Statistics and Research case decks · pediatric reference values.