# Hypothesis Testing - One versus Two Tail Tests.pptx -...

• 14

This preview shows page 1 - 4 out of 14 pages.

Hypothesis Testing Steps 1. State null and alternative hypotheses. 2. Choose level of significance. 3. Decide on the test to use (t test, z test, etc.) 4. Find critical values and graph regions of rejection and acceptance over the standard normal curve. 5. Collect data and compute test statistic. 6. Decide whether the test statistic lies in the rejection or acceptance region of the curve. 1
2 Hypothesis Testing - Step 1 The Null Hypothesis The null hypothesis (H 0 ) assumes that there is no difference: the equals sign is always shown in the null hypothesis. H0: μ1 = μ2, or μ1 <= μ2, or μ1 >= μ2 The alternative hypothesis will hypothesize one of three things: 1. One mean has increased: H 1 : μ > μ 0 This test is an upper tail test 2. One mean has decreased: H 1 : μ < μ 0 This test is a lower tail test 3. The means do not equal each other: H 1 : μ ≠ μ 0, This is a two tail test You tell the type of test by looking at the alternative hypothesis
Hypothesis Testing – Step 2 Level of significance (alpha) 3 Alpha, α, is the statistically significant threshold at which we reject the null hypothesis.
• • • 