Statistical tests based on subgroup results help you find out whether an assumption about your production is right. They answer questions as to whether two batches are equal with respect to a certain characteristic or the variation of a machine improved after maintenance.

Two complementary hypotheses are the heart of these statistical tests. The decision for one of these two hypotheses is based on a test statistic calculated from a subgroup. You compare this test statistic to the critical value and the result leads to the acceptance or rejection of the null hypothesis. The remaining risk of making a wrong decision is specified, too. How well are you acquainted with this subject?

1. Which test is inappropriate to determine differences in variation?

• Levene’s test
• t-test
• F-test

2. Which statement about the p-value is not correct?

• The p-value indicates the probability that a test result is only a random one.
• If the p-value is small, the null hypothesis will not be rejected.
• The p-value indicates the residual risk of making a wrong decision.

3. What is the “power of a statistical test“?

• Probability of accepting the alternative hypothesis if the alternative hypothesis is true
• Probability of accepting the null hypothesis if the null hypothesis is true
• Probability of accepting the null hypothesis when the null hypothesis is not true

4. Which pair describes two normality tests?

• t-test and Kolmogorow-Smirnow test
• F-test and Levene’s test
• Shapiro-Wilk test und Anderson-Darling test

5. Which alternative hypothesis is true?

• µ₁ = µ₂
• sigma₁² = sigma₂²
• µ_A unequal µ_B

Our Q-QUIZ is published once a month. You can find the answer to all questions of the current quiz online after the release of the next quiz.
This quiz was originally published in the April issue 2016 of the German magazine QZ Qualität und Zuverlässigkeit at http://www.qz-online.de/.