Terminology

Question 1

Incidence

Question 2

Prevalence

Question 3

Absolute risk

Answer 3

The number of events (good and bad) in a treated (exposed) or control (non-exposed) group divided by the number of people in that group.

Question 4

Relative risk (Exposure and disease)

Question 5

Odds ratio (Exposure and disease)

Answer 5

odds of the event in the exposed group divided by odds of the event in the non-exposed group

Question 6

Relative risk vs absolute risk increase or decrease

Question 7

Number needed to treat

Answer 7

1/ARR (absolute risk reduction)

Question 8

Number needed to harm

Question 9

Hazard ratio

Question 10

Sensitivity of test

Question 11

Specificity of test

Question 12

Positive predictive values - depends of prevalence/ pre-test probability. Reason why only patients at high clinical suspicion including epidemiological considerations.

BMJ covid test tool

Question 13

Negative predictive values

Question 14

Confounding factors

Question 15

P-value

Answer 15

The chance that the null hypothesis is true. (i.e. event happened in random, not in association with anything) — using a pre-test likelihood

Value of <0.05 in p-value means that there is less than 1 in 20 chance that the event happened by chance, hence allowing us to ‘reject’ the null hypothesis and proving our proposed hypothesis.