8.3 - Completing the methodology of hypothesis testing

In the previous section we outlined the important components of a hypothesis test:

  • We assume the claim in the null hypothesis is true.
  • We can then relate this assumption to a sampling distribution.
  • We can then argue whether or not the claim should be rejected, depending on where the sample statistic sits in this sampling distribution.

But just as we did for confidence interval estimation, to have a complete method of hypothesis testing, we will have to relate the sampling distribution to the standard normal distribution, Z.

In this section we will see the formal and complete method for testing a hypothesis by transforming the sampling distribution and sample statistic into Z.

Learning objectives

In this section you will learn about:

  1. the test statistic of a sample statistic
  2. the level of significance
  3. critical values and the region of rejection for a hypothesis test
  4. the impact of whether a hypothesis test is one-sided or two-sided on critical values and the region of rejection
  5. the steps followed to conduct a hypothesis test