Calculate a finite-population sample size for quality testing a set of contract reviews. The model is suited to checking items such as playbook adherence, required clauses, approval routing, metadata accuracy, or completion of review steps across a defined contract population.
The result is a statistical planning figure, not a rule for legal sufficiency. A defensible contract audit also depends on how the population is defined, how contracts are selected, whether risk strata should be sampled separately, and what constitutes an exception. Use a 50% expected exception rate when uncertainty is high and a conservative sample is preferred. For portfolios with materially different contract types or risk levels, separate stratified samples may provide more useful findings than one blended sample.
1. Define the contract population
Enter the total agreements included in the audit scope.
2. Choose confidence
Set the confidence level for the proportion estimate.
3. Set precision
Enter the margin of error in percentage points.
4. Estimate the exception rate
Use a prior audit result or a conservative assumption for the expected exception proportion.
5. Apply the result
Round up to the displayed sample size and select contracts using the audit methodology appropriate to your objective.
Where z is the two-sided normal critical value for the confidence level, p is the expected exception proportion, e is the margin of error as a decimal, and N is the finite population size. The displayed sample is rounded up.
The result is a planning estimate based entirely on the values entered. Use it to compare scenarios and workload assumptions, not as a legal conclusion.
Confirm applicable law, contracts, policies, court orders, holds, and professional requirements before making compliance or legal decisions.
Often that is more informative. If risk groups differ materially, a stratified audit can prevent a large low-risk group from overwhelming the sample.
It is the targeted sampling precision for estimating a proportion, expressed in percentage points. It does not measure legal risk or the severity of an exception.
Yes, if the prior population and process are comparable. Otherwise a 50% rate is a conservative default for sample-size planning.
Higher confidence generally requires a larger sample. The appropriate level depends on the audit purpose, cost, risk, and any governing requirements.
No. Sampling supports inference under stated assumptions and a suitable selection method; it does not guarantee that every unsampled contract is free of issues.