This preview has intentionally blurred sections. Sign up to view the full version.
Unformatted text preview: a one-tailed test. 3. Decide on a significance level (alpha-value): .05 4. Perform our test in JMP a. Select Analyze b. Fit Y by X c. X is always the treatment column d. Y is always the values (sales, number of customers) e. Click ok f. Click on the red arrow and select “t-test” g. Depending on whether it is a one or a two tailed test, read the correct P-value 5. Decide: if P-value is less than .05, reject the Ho. . Else, you fail to reject Ho “If P is low, Null must go.” REMEMBER: We only reject or fail to reject Ho. • We could have two kinds of error. . because remember, we’re making an inference about the population. So, there is a chance we could be wrong. o If we rejected Ho, when in fact, it was true – Type I Error o If we failed to reject Ho, when in fact, it was false – Type II Error...
View Full Document
- Fall '13
- Interest, Null hypothesis, Hypothesis testing, Statistical hypothesis testing, Type I and type II errors