What is the standard p-value for Anderson-darling test in SAS

[Monica_1134]

Hi,

I analysis a set of data with Weibull distribution.

There is a automatic calculate about Anderson-Darling test and its p-value.

But I didn't find the standard p-value in SAS that let me know the distribution whether has a good fit.

I know the regular standard value of p is 0.05.

When p-value <0.05, we reject the hypothesis, vice versa.

Is the standard p-value also equal to 0.05 in SAS? or is 0.01 or 0.1?

Thank you.

[Ksharp]

No. I don't think so. But maybe @Rick_SAS know the answer .

[Rick_SAS]

By default, most SAS procedures use alpha=0.05 as the significance value for confidence intervals (e.g., 95% confidence). However, the significance level does not affect the computation of a p-value.

A p-value for a hypothesis test is a computation that indicates the likelihood that the data sample is a random draw from the null distribution. The p-value is a probability. It is the probability that you would observe the test statistic for a random sample if the null hypothesis is true. You, the user of the procedure, can use the p-value to decide whether or not you should reject the null hypothesis, based on the data that you have observed.

As you say, it is common practice to reject the null hypothesis when the p-value is less than 0.05.