Abstract: The significance test is the most primary statistical hypothesis test, and it's basic principle is the principle of little probability. The interval test in clinical trial is the extension of the significance test, which is used to testify whether the difference between two populations is within a certain interval. In the confidence interval test, firstly, we find the confidence interval of the difference between two treatments' effects, and then we can decide whether it is non-inferior, equivalent or superior or not through comparing the confidence interval with the margin. Through the transformation of equations, it can be revealed that the most essential difference between the significance test and the interval test is the margin, which has the clinical meaning, is included in the interval test. In this paper, the consistency is confirmed between the interval test and the confidence interval test, so we can use the confidence interval test to achieve the result of the interval test.

Key words: Significance test, Interval test, Non-inferiority test, Equivalence test, Superiority test, Confidence interval test