Data considerations for Goodness-of-Fit Test for Poisson

To ensure that your results are valid, consider the following guidelines when you collect data, perform the analysis, and interpret your results.

The data must be counts per unit, such as the number of calls per hour to a call center or the number of defects per unit in a shipment

If you have continuous data, such as length, weight, or temperature, and want to determine whether the data follow a normal distribution, use Normality Test.

The sample data should be selected randomly

In statistics, random samples are used to make generalizations, or inferences, about a population. If your data are not collected randomly, your results may not represent the population. For more information, go to Randomness in samples of data.

The expected counts for each category must not be too small

If the expected counts (also called expected frequencies) for any category is less than 5, the results of the test may not be valid. If the expected counts for a category are too low, you may be able to combine that category with adjacent categories to achieve the minimum expected count.

For example, a finance department has five categories to classify the number of days that invoices are overdue: 15 or less, 16–30, 31–45, 46–60, and 60 or more. The category for 60 days or more has a low expected count, so the finance department combines it with the category for 46–60 days to create a combined category for 45 days or more.

By using this site you agree to the use of cookies for analytics and personalized content.  Read our policy