Statistics and Research – Exam Review Set 4

What this deck covers

Statistics and Research – Exam Review Set 4 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 paediatric board, MRCPCH and licensing examinations. Written from published guidelines and standard paediatric textbooks, with the source named on every answer.

The 50 cases, in order

1. One number for a whole curve
2. Where to put the line
3. A test that did not settle it
4. Brilliant in clinic, useless outside
5. Everyone else went home
6. Flagged before an operation
7. Nineteen normal, one not
8. The numbers moved, the child did not
9. Eighty-eight, ninety-two, ninety-five
10. Flagged against the wrong ruler
11. Forty-one children, one peak
12. Ninety, then sixty-eight
13. Five of twelve in the dormitory
14. Sixty names on both
15. One in five, then one in a hundred
16. Halfway, and she wants a look
17. Two thirds in, going nowhere
18. Why a computer decides
19. In and out under one protocol
20. Answered somewhere else first
21. He says no, they say yes
22. No time to ask anyone
23. Something the study never sought
24. Forty thousand records, no consent
25. Signed for at birth, sixteen now
26. Two surgeons, one audit
27. Asking the doctor to choose
28. Which one should they fear
29. A word that meant nothing
30. Twenty per cent by when
31. Thirty-eight children in all
32. Same numbers, different claim
33. Too few to power a trial
34. Ninety-six per cent, one belief
35. Ninety-two against sixty-one
36. A few practices, every week
37. An empty card, posted anyway
38. Fewer centres, fewer cases
39. Well enough to travel
40. Doubled the week the rules changed
41. Three years on, missing children
42. Overridden twice in a year
43. Learning from ten years of us
44. A score nobody can explain
45. Forty a day, one of them real
46. Praised on the crude number
47. Three years that could not kill
48. Forty per cent, or fewer
49. Caught early, or caught quiet
50. Places measured, children not

Diagnoses and management options tested

Across the fifty cases you are asked to choose between options such as: Prevalence is lower in general practice, Arrange the ultrasound first, Metabolic bone disease of infancy, The incidence rate in the school, Granted in full, A crossover trial, Only children whose parents are present, Nothing; the parents’ consent covers it, The prior, The p value from a conventional analysis, As a genuine doubling of the illness, Ignore district, as it was not supplied.

Clinical pearls from this deck

• The area is a ranking, not a score: how often the sick child comes out above the well one. It survives any cut-off and tells you nothing about the one you will use.
• The curve tells you what is possible, never what is right. Put the cut-off where the cheaper mistake is the one you make.
• A test moves the probability, it does not replace it. Start high enough and a negative result still leaves you high.
• Test the floridly ill against the perfectly well and everything looks brilliant. The children who actually walk in are in between.
• If only the positives get the operation, the misses are never counted. The sensitivity was decided by the design, not by the test.
• The range was drawn around 95 per cent of healthy children, so it was always going to flag the other five. Ask how far out, not whether out.

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.