If one or more parameters are left unspecified in a goodness-of-fit test, they must be estimated from the sample data and one degree of freedom is lost for each parameter that must be estimated.

Question

Quizplus · Accepted Answer

In a goodness-of-fit test, if parameters of the theoretical distribution are not specified and need to be estimated from the sample data, one degree of freedom is lost for each estimated parameter. This is because each parameter estimated from the data uses up information that would otherwise contribute to the degrees of freedom in the test statistic's distribution.

If One or More Parameters Are Left Unspecified in a Goodness-Of-Fit