Problems in GARP's 2020 FRM material


New Member
Hi! I have a concern about QA chapter 9 answer to the question 9.4, which says that the probability of including a single irrelevant regressor is 1 - alpha, where alpha is the test size. But shouldn't it actually be alpha? As I am understanding this is that including the irrelevant regressor is incorrectly rejecting the true 0-hypothesis, which is a Type 1 error and the probability of that is equal to the test size. Or am I missing something?


Well-Known Member
Hi @lucaslim ,

Thanks for your question.

I did not see the exact page, but your question seems simple enough to say yes - the calculation is correct IF:
  • The two-year Treasury bond is semi-annually paid ($1.25 paid per half a year)
  • 0.996512 corresponds to the 0.5 year zero rate
  • 0.990569 corresponds to the 1.0 year zero rate
  • 0.982707 corresponds to the 1.5 year zero rate
  • 0.972977 corresponds to the 2.0 year zero rate
Perhaps you can be more specific with your question? Like if you think there is a problem in the calculation with the discount factors or something else you are suspicious at. Hope this is helpful!

David Harper CFA FRM

David Harper CFA FRM
Staff member
I agree with @lushukai the coupons (of $1.25 each) and the final future cash flow ($100.25) are multiplied by the discount factors which returns their present values; the sum of the present values is the bond's theoretical price.