- CFA Exams
- CFA Level I Exam
- Topic 1. Quantitative Methods
- Learning Module 6. Hypothesis Testing
- Subject 9. Tests Concerning Differences between Means with Independent Samples

###
**CFA Practice Question**

Which of the following statements is not true when it comes to conducting hypothesis tests about the equality of the variances of two populations?

A. Two distinct degrees of freedoms are used, one representing each population, in order to determine the critical value.

B. This type of test mandates that the underlying populations be normally distributed.

C. The not-equal-to-alternative hypothesis implies that if the test statistic is greater than the critical value implied by the level of significance, then the null hypothesis is rejected.

**Explanation:**The proper distribution for such a test is an F-distribution. The not-equal-to-alternative hypothesis implies that if the test statistic is greater than the critical value implied by (the level of significance divided by two), then the null hypothesis is rejected. Remember, whenever you have a two-tailed test, the level of significance must be divided in two, with the resulting numbers allocated to both tails. For instance, a 10% level of significance for a two-tailed test would imply that each tail area represents 5%.

###
**User Contributed Comments**
5

User |
Comment |
---|---|

achu |
nasty question, I agree. But this might be fair game for a (nasty) exam question. F-test is the one, not Chi-square |

lanhuongnguyen |
Divide , divide.... |

jpducros |
For answer A, do the degrees of freedom necessarily need to be distinct ? |

Patdotcom |
I really dont get it!! It is asking for FALSE option. If C is true then it cannot be right… am I wrong? |

rojaslav |
Since it is a not-equal-to-alternative test, this means that you should use the two sided level of significance. Literally, the only thing missing in option C to be correct is TWO-SIDED level of significance. |