Table 6.

Interpretation of common measurements used in research studies

Measurement	Use	Limitations	Magnitude of associationa
Odds ratio (OR)	Determines the association between 2 variables (exposure to outcome)	Can be used in any study type but not always useful as it exaggerates the risk	OR 1.0 to 1.5 (further research required) OR 1.5 < 2.0 (worth further investigation) OR 2 < 4 (possibly important) OR 4.0 (pretty strong)
Risk ratio/Relative risk (RR)	Determines risk of the incidence of an exposure to the incidence without the exposure	Study design must be representative of the population; cannot be used on case–control studies Note: RR is a more accurate and preferable measure of risk	RR 1.0 to 1.5 (further research required) RR 1.5 < 2.0 (worth further investigation) RR 2.0 < 4.0 (possibly important) RR 4.0 (pretty strong)
Hazard ratio (HR)	Determines how 1 group changes over another; based on rate of change between 2 hazards; typically used in survival studies	Usefulness based on consistency in the rate of change within 2 groups; used to measure certain “points in time”; does not measure “means” over time	HR 1 (no association) HR 1.5 < 2.0 (weak association) HR 2.5 < 3.5 (moderate association) HR 3.5 (strong association)
Confidence interval (CI)	Intervals in which the population statistic could lie; typically uses a 95% confidence interval as the threshold for significant results. (Provides a range of values between which the results lie)	N/A	Range of values will be based on the OR, RR or HR measured and thus interpreted according to the above scales The narrower the CI, the more precise the estimate
P value	Reports the probability that the sample statistic was produced from random sampling of a population Significance values are determined by the researchers prior to commencement of the study set at a minimum of <0.05 (<5% probability that results are due to chance)	N/A	Significance based on what the researchers determined at the beginning of the study; no higher than p < 0.05

Table adapted from George A, Stead TS, Ganti L. What’s the risk: differentiating risk ratios, odds ratios and hazard ratios? Cureus. 2020;12(8):e10047.

^aMagnitude of association adapted from http://utstat.utoronto.ca/reid/odds.pdf and http://onbiostatistics.blogspot.com