Concept Architecture
Concept
Theoretically, Incidence Rate Ratio (IRR) is a comparative epidemiological measure that quantifies the relative rate at which new events occur in one population compared with another while accounting for differences in person-time at risk. It represents the ratio of incidence rates between exposed and comparison groups and is founded on person-time incidence theory. The concept exists to compare event occurrence when follow-up durations differ between individuals or study groups.
Mathematically, the Incidence Rate Ratio is defined as the ratio of two incidence rates, each calculated by dividing the number of observed events by the total person-time at risk. It is a dimensionless relative measure in which an IRR greater than 1 indicates a higher event rate in the exposed group, an IRR less than 1 indicates a lower event rate, and an IRR equal to 1 indicates identical incidence rates.
In practice, the Incidence Rate Ratio is estimated using cohort studies, surveillance systems and clinical studies with variable follow-up periods. It is commonly calculated using Poisson regression or negative binomial regression and is widely applied in epidemiology, pharmacovigilance and health economic evaluations where person-time is the appropriate denominator.
Purpose
Used to compare disease or event rates between populations while accounting for person-time at risk, evaluate exposure effects, quantify treatment effectiveness and support epidemiological and health economic analyses.
Mathematical Formulae
Primary Formula
IRR = IR? / IR?
where:
- IRR = incidence rate ratio
- IR? = incidence rate in the exposed group
- IR? = incidence rate in the unexposed or comparison group
Supporting Formulae
IR = Events / Person-time
IRR = (E? / PT?) � (E? / PT?)
95% CI = exp[ln(IRR) � 1.96 ? SE(ln(IRR))]
SE(ln(IRR)) = �[(1/E?) + (1/E?)]
where:
- E? = events in the exposed group
- E? = events in the comparison group
- PT? = person-time in the exposed group
- PT? = person-time in the comparison group
Related Mathematical Methods
- Incidence Rate
- Rate Ratio
- Relative Risk
- Poisson Regression
- Negative Binomial Regression
- Person-Time Analysis
- Confidence Interval Estimation
Example
A cohort study follows two treatment groups.
Treatment group:
- 40 events during 2,000 person-years
IR? = 40 / 2,000 = 0.020 events per person-year
Control group:
- 25 events during 2,500 person-years
IR? = 25 / 2,500 = 0.010 events per person-year
Incidence Rate Ratio:
IRR = 0.020 / 0.010 = 2.0
The treatment group experiences twice the incidence rate of the outcome compared with the control group.
Excel Implementation
| Function | Example Formula | Health Economics Application |
|---|---|---|
| Division | =(B2/C2)/(D2/E2) | Calculates the Incidence Rate Ratio using events and person-time for two groups. |
| LN | =LN(F2) | Computes the natural logarithm of the Incidence Rate Ratio for confidence interval estimation. |
| EXP | =EXP(LN(F2)-1.96*G2) | Calculates the lower 95% confidence interval. |
| EXP | =EXP(LN(F2)+1.96*G2) | Calculates the upper 95% confidence interval. |
VBA (Optional)
A VBA macro can automatically calculate incidence rates, Incidence Rate Ratios, confidence intervals and comparative person-time summaries across multiple studies or surveillance datasets.
Sources
- Rothman KJ, Greenland S, Lash TL. Modern Epidemiology. 4th ed.
- Clayton D, Hills M. Statistical Models in Epidemiology.
- Breslow NE, Day NE. Statistical Methods in Cancer Research. Volume II: The Design and Analysis of Cohort Studies.
- Kirkwood BR, Sterne JAC. Essential Medical Statistics. 2nd ed.
- Drummond MF, et al. Methods for the Economic Evaluation of Health Care Programmes. 4th ed.
Related Concepts (2)
Library
Publications
1
Statistical Analysis of Cost-Effectiveness Data — Willan & Briggs, 1st Edition ed., 2006 (John Wiley & Sons)
A synthesis of statistical methods for analysing cost-effectiveness data, including net-benefit regression, confidence intervals for the ICER, cost-effectiveness acceptability curves, and covariate adjustment. Part of the Wiley Statistics in Practice series.
BookView source →
Frequently Asked Questions (6)
What is an incidence rate ratio?
A measure comparing the incidence rate of an outcome between two groups, accounting for differences in total person-time at risk.
Source: Rothman KJ, Greenland S, Lash TL. Modern Epidemiology. 3rd ed. Lippincott Williams & Wilkins; 2008.
Why does an incidence rate ratio account for person-time?
An incidence rate ratio compares the incidence rate of an outcome between two groups, dividing one rate by the other. It accounts for person-time because it is built from rates that use total time at risk in their denominator, so it fairly compares groups whose members were followed for different lengths. This suits situations where people enter and leave over the study, or are observed for unequal periods, which a simple risk ratio based on counts would mishandle. Comparing rates that respect time at risk is its point. Rothman and colleagues (2008) describe this measure.
Source: Rothman et al. 2008
How is an incidence rate ratio calculated?
An incidence rate ratio is calculated by dividing the incidence rate in one group by the incidence rate in another, where each incidence rate is the number of new events divided by the total person-time at risk in that group. Person-time captures both the number of people and how long each is followed. So an incidence rate ratio is calculated as the ratio of two incidence rates, each based on events per person-time, which properly accounts for differences in follow-up duration between individuals and groups, distinguishing it from measures based on simple counts or proportions that ignore the time each person is at risk.
Source: Rothman, Greenland & Lash 2008
When is an incidence rate ratio used?
An incidence rate ratio is used when follow-up varies between individuals, as in cohort studies where people are observed for different lengths of time, so that rates based on person-time are more appropriate than simple risks. It is suited to ongoing or recurrent events and to open populations. So an incidence rate ratio is used to compare the rate of new events between groups where accounting for person-time matters, which is common in longitudinal studies, since using rates rather than proportions correctly handles the varying time individuals spend at risk, giving a fairer comparison of how quickly the outcome occurs.
Source: Rothman, Greenland & Lash 2008
How does an incidence rate ratio differ from a risk ratio?
An incidence rate ratio compares incidence rates based on events per person-time, while a risk ratio compares the cumulative probability, or risk, of an event over a fixed period based on proportions. The rate ratio accounts for varying follow-up through person-time, whereas the risk ratio assumes a common period and uses simple proportions. So the two differ in whether they use rates or risks: the incidence rate ratio suits situations with differing follow-up and recurrent events, and the risk ratio suits fixed-period comparisons, and although they often give similar values for rare outcomes, they are conceptually distinct measures.
Source: Rothman, Greenland & Lash 2008
How is an incidence rate ratio interpreted?
An incidence rate ratio is interpreted as the relative rate of the outcome between groups: a value of one indicates equal rates, above one a higher rate in the group of interest, and below one a lower rate. It expresses how many times faster the outcome occurs in one group than another per unit of person-time. So an incidence rate ratio is interpreted as how many times greater or smaller the rate of new events is between groups, a relative measure interpreted alongside absolute measures such as the rate difference.
Source: Rothman, Greenland & Lash 2008
Trust Record
Verified by Dr Darrin Baines
British health economist
Professional identity: darrinbaines.org
Verification date: 9 Dec 2025
Content version: 1.0.0
Canonical Identity
- Term code
- HE-ES-RM-011
Stable URI · Machine-readable · Resolvable · CC BY 4.0