Measure of Association & Causality

Question 1

What is the equation for Relative Risk (RR)?

Answer 1

RR = incidence in the exposed / incidence in the unexposed
Or
RR = [a/(a+b)] / [c/(c+d)]

Question 2

What is the equation for Odds Ratio (OR)?

Answer 2

OR = odds of exposure in cases / odds of exposure in controls
Or
OR = ad / bc

Question 3

What does it mean when OR = 1?

Answer 3

Exposure does not have an association with the outcome. This is not significant.

Question 4

What does it mean when OR < 1?

Answer 4

The exposure is associated with lower odds of outcome.

This is significant, depending on CI.

Question 5

What does it mean when OR > 1?

Answer 5

The exposure is associated with higher odds of outcome.

This is significant, depending on CI.

Question 6

What does the Number Needed to Treat (NNT) tell us?

Answer 6

The number of subjects needed to be treated to prevent 1 outcome from occurring.

Question 7

What is the formula for NNT?

Answer 7

NNT = 1 / ARR

Question 8

What does the Attributable Risk (AR) tell us?

Answer 8

Represents the difference between incident rates of disease in exposed vs unexposed groups.

It provides an estimate of the expected benefit for the exposed group if the exposure was removed.

Question 9

What is the formula for AR?

Answer 9

AR = Incidence in exposed — Incidence in unexposed
Or
AR = [a/(a+b)] - [c/(c+d)]

If the result is:

• Positive: Absolute Risk Increase (Harmful)
• Negative: Absolute Risk Reduction (Protective)

Question 10

What does the Absolute Risk Reduction (ARR) tell us?

Answer 10

It shows us how protective the treatment is by measuring the absolute difference between the control/placebo group and the exposed/treatment group.

Question 11

What is the formula for ARR?

Answer 11

ARR = Incidence in unexposed — Incidence in exposed
Or
ARR = [c/(c+d)] — [a/(a+b)]

Question 12

What does the Relative Risk Reduction (RRR) tell us?

Answer 12

How much the treatment/exposure reduced the risk of the outcome in the exposed group compared to the unexposed group.

Question 13

What is the formula for RRR?

Answer 13

RRR = 1 — RR

Question 14

A study investigated the relationship between the risk of developing high blood pressure and coffee in the past month (yes/no). 200 cases with high blood pressure were diagnosed in 2018 between the ages of 18–80 years and 500 controls from the same geographical area as the cases were interviewed about their coffee consumption and other potentially aetiological variables (confounders). If the OR (odds ratio) =1.5, 95% confidence interval (CI)=0.5 – 2.0, what does this mean?

a. The odds of having high blood pressure in the past month is higher in those who consumed coffee compared to those that didn’t, but this is not significant
b. The odds of having high blood pressure in the past month is lower in those who consumed coffee compared to those that didn’t, but this is not significant
c. The odds of having high blood pressure in the past month is higher in those who consumed coffee compared to those that didn’t, but this is significant
d. The odds of having high blood pressure in the past month is lower in those who consumed coffee compared to those that didn’t, but this is significant

Answer 14

a. The odds of having high blood pressure in the past month is higher in those who consumed coffee compared to those that didn’t, but this is not significant

Even though the result falls within the CI, it is not significant because 1.5 crosses 1.