Stat 1000: Compute a P-Value every time you perform a hypothesis test

Published: Mon, 11/24/14

Grant's Revised Steps to Test Hypotheses

Important Note:  Unlike what I instruct in my book, make sure that you compute a P-value every single time that you perform a hypothesis test.  They have decided to not teach about critical values this term, so there is no need to use Table D to get z* or t*, the critical value, for any hypothesis test.  Because you are not using critical values, it therefore becomes essential to compute a P-value. 

Your five steps to test a hypothesis should now always be:

  1. State the Hypotheses and so establish whether the test is upper-tailed, lower-tailed, or two-tailed.
  2. State the given level of significance, alpha.  Let alpha = 5% if none is given.
  3. Compute the test statistic using the correct formula for z or t.
  4. Compute the P-value by marking the test statistic on a bell curve and shading the appropriate region according to your alternative hypothesis.
  5. State your conclusion knowing that you always reject Ho if the P-value < alpha.