Correction for Continuity

---

The correction for continuity is used in testing whether a proportion (p) differs significantly from a hypothesized value of the proportion (π).

Click here for the test based on the normal distribution.
Click here for the test based on the chi square distribution.

It corrects for the fact that the sampling distribution of a proportion is not a continuous distribution. The correction should only be used when a single sample proportion is compared with the population proportion. It should not be used when there are more than two possible outcomes for each subject or for the chi square test of independence. The correction for continuity consists of subtracting .5/N from the absolute value of the difference between p and π or of subtracting .5 from the absolute value of the difference between expected and observed cell frequencies.