Advanced Poisson Rate Test Calculator

Calculator Inputs

Test type

Alternative hypothesis

Alpha

Observed events

Exposure time or area

Null rate

Sample 1 events

Sample 1 exposure

Sample 2 events

Sample 2 exposure

Null rate ratio

Example Data Table

Scenario	Events	Exposure	Reference	Interpretation Goal
Support tickets per staff hour	18	2500	Null rate = 0.006	Check whether workload exceeds the benchmark.
Machine faults on Line A	18	2500	Compared with Line B	Compare reliability across two production lines.
Machine faults on Line B	11	2400	Rate ratio null = 1	Assess whether the event rates are equivalent.

Formula Used

One-sample rate estimate: r = x / t, where x is the observed event count and t is total exposure.

One-sample test statistic: z = (x - λ₀t) / √(λ₀t), where λ₀ is the null rate.

Two-sample rate ratio: RR = (x₁/t₁) / (x₂/t₂).

Two-sample log test statistic: z = [ln(RR) - ln(RR₀)] / √(1/x₁ + 1/x₂).

Confidence interval for the ratio: exp[ln(RR) ± z_α/2 × SE].

This calculator uses normal approximations, which are most reliable when counts are moderate and exposure is measured consistently.

How to Use This Calculator

Select either the one-sample or two-sample Poisson rate option.
Choose the alternative hypothesis that matches your research question.
Enter event counts and the related exposure amounts.
For one-sample testing, provide the null rate benchmark.
For two-sample testing, provide the null rate ratio, usually 1.
Set alpha, then submit the form to view results.
Read the p value, interval, and decision statement together.
Use the CSV or PDF buttons to export findings.

Frequently Asked Questions

1. What does a Poisson rate test measure?

It tests whether an observed event rate matches a benchmark or whether two event rates differ after accounting for exposure time, distance, area, or population.

2. When should I use exposure values?

Use exposure whenever observation windows differ. Exposure standardizes counts so rates remain comparable across samples, periods, machines, patient-years, or production runs.

3. What is the null rate?

The null rate is the benchmark event frequency assumed under the null hypothesis. The test checks whether the observed data depart from that target.

4. What does the p value tell me?

The p value shows how compatible the observed data are with the null hypothesis. Smaller values indicate stronger evidence against the stated null rate or ratio.

5. Why does the calculator require positive exposure?

A rate divides events by exposure. Without a positive exposure value, the rate is undefined and the comparison cannot be interpreted statistically.

6. Why are zero counts limited in two-sample mode?

The rate-ratio method here uses logarithms. A zero count makes the log ratio unstable, so the calculator stops and asks for positive counts.

7. Are these results exact?

No. This page uses normal-approximation formulas for speed and clarity. They work best with moderate counts and may be less stable for sparse events.

8. How should I report the result?

Report the rate or rate ratio, confidence interval, z statistic, p value, alpha level, and a plain-language conclusion tied to your study context.