The probability plot for the P chart diagnostic test shows how well your data fit a binomial distribution.
If your data follow a binomial distribution closely, then the plotted points fall close to the diagonal reference line.
Ratio of observed variation to expected variation
The ratio of observed variation to expected variation compares the variation in your data to the variation that you would expect based on a binomial distribution. The ratio is expressed as a percentage.
A ratio that is close to 100% indicates that your data exhibit the expected amount of variation for a binomial distribution. Compare the ratio to the 95% upper confidence limit or the 95% lower confidence limit to determine whether your data exhibit significant overdispersion or significant underdispersion:
If the ratio is greater than the upper confidence limit, then your data exhibit significant overdispersion.
If the ratio is less than the lower confidence limit, then your data exhibit significant underdispersion.