- CFA Exams
- CFA Level I Exam
- Topic 1. Quantitative Methods
- Learning Module 6. Hypothesis Testing
- Subject 3. Test Statistic and Significance Level

###
**CFA Practice Question**

We want to test the claim that a steady diet of wolfsbane will cause an 18-year-old werewolf to lose EXACTLY 10 lbs. over 5 months. A random sample of 49 werewolf was taken, yielding an average weight loss over 5 months of 12.5 lbs with S = 7 lbs. Let alpha = .02. What is the calculated value suitable for testing the above hypothesis?

B. 7 x 2.5

C. 2.5

A. 12.5

B. 7 x 2.5

C. 2.5

Correct Answer: C

t(calculated) = (12.5-10)/(7/SQRT(49)) = 2.5

###
**User Contributed Comments**
9

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

isida |
test statistic question: (sample statistic - null value) / standard error standard error = standard deviation / sqrt N |

Masterkang |
Obviously, he read to many Harry Potter Books... |

achu |
we know it's t-test because S sample sd, not population std dev. |

steved333 |
Yes, but sample size is large, so it doesn't matter. T-stat is the same as Z in this case. |

poomie83 |
Was alpha there as useless information? |

ybavly |
@poomie83 yes |

johntan1979 |
Agree with steved333. n>30, so Z. |

sgossett86 |
the equation for variance is single bernoulli variable |

Shaan23 |
You guys need to read the notes. One we dont know if this is normal or not. Population variance is unknown. Whenever population variance is unknown always jump to t-test. But remember t-test approaches the z test when n becomes big. |