8.6: Testing a Hypothesis

You want a plan for interpreting the statistical test numbers. For this example, the hypothesis is there will be a difference between the two groups (treatment vs. control):

• Set α at .05.
• Run the statistical test and obtain the result and p value.
• You want a high t-test value, usually above 1.96, and a low p value.
• t-test value = 3.96, p = .02. This p value is less than .05, so it is significant.
• Reject null, state the t-test value and the p value
• Write or state, “The t-test was t = 3.96 and was significant at p < .05.”
• If you have a low t-test value, usually below 1.96, and a high p value, then…
• For example, t-test value = 1.21, p = .15. This p value is greater than .05, so it is not significant.
• Retain null, state the t-test value and the p value
• Write or state, “The t-test was t = 1.21 and was not significant, p = .15.”

Some notes about writing the p value.

• According to APA style, note that when the test result is not significant, give the statistical test value and the actual p value. For example, “The t-test was t = 1.21 and was not significant p = .15.”
• If the test result is significant, there is no need to go further than the two decimal points. Write it out if the p value is from .05 to .01. Anything below .01, you can write p < .01.
• For example, “The t-test was t = 3.96 and was significant, p = .03.”
• Or “The t-test was t = 10.01 and was significant, p < .01.”

A note about not needing to write out the p value result beyond .01. Keep in mind that you should never write the following: p < .001, never say “highly significant,” “trending towards significance,” or “approaching significance.” I will explain later in this section, but for now, it is misleading to write everything mentioned in the previous sentence.

---