Probability of error

Probability of error is a statistical term for:

• the probability of a Type I error in a test or
• the rate of misclassification when assessing a classifier.

The maximum permissible error probability specified for a statistical test is also referred to as the level of significance . In the event that the null hypothesis is rejected at this level, it corresponds to the maximum probability of the type I error that the null hypothesis is rejected even though it is correct. The smaller this probability of error, the greater the probability of the type 2 error that the null hypothesis is not rejected even though it is false.

The probability of error does not match the p-value calculated when you ran a test . Nor does it say the probability of a hypothesis being correct.