Hypothesis Testing: The P- Value
In the previous section covering hypothesis testing for one parameter, we discussed the methods used in testing a claim for a population mean. The conclusion of the test was based upon whether we reject or fail to reject the null hypothesis, a decision determined by the position of the test statistic relative to the rejection region. This approach is known as the classical approach.
Many professional articles and software applications (such as Microsoft Excel) use another method, the probability, or P- Value. Essentially, the P- Value is the probability of observing another mean value that is at least as extreme as the value found from the sample data.
One advantage of the P- Value approach is that it can involve a comparison of the test statistic against the critical value to reach a decision, or the conclusion may be based upon the P- Value alone.
The classical approach vs. the P- Value approach
Determining significance by P- Value alone