QM

CFA Level II
#1

50 observations regression results Y=.78-1.5x SEE .40 Std error of coefficient .45 at 95% confidence a. t=-3.750, slope is different from zero b.t=3.750, slope is different from zero c.t=-3.333, slope is signicifantly negative

#2

C???

#3

would go with c too

#4

C

#5

no its not c - wait for CP when he comes he will solve it but keep trying

#6

Hmmm…why would you divide the Coeff by the SEE?

#7

Alright, I’m guessing A then - it’s gotta be some story about the standard error which is not equal to the estimated s_b_1… multiply it by sqrt((n-1)/n) or something. Gotta look that up later. Am I guessing right?

#8

You sure its not C? I did this question last week and I’m almost certain that was the answer…

#9

No way we are dividing here by SEE. Ans has to be C by the very fact that -1.5/0.45 = -3.333

#10

Agreed. Dividing by the SEE makes no sense whatsoever…

#11

whts the answer?

#12

If you have to say slope is significantly negative - can you do the comparison against 0? For the t -1.5 - 0 / .45 = -3.333 -> implies slope is different from 0. But does not mean that slope is significantly negative, does it? so choice has to be A, by elimination.

#13

cpk123 Wrote: ------------------------------------------------------- > If you have to say slope is significantly negative > - can you do the comparison against 0? For the t > > -1.5 - 0 / .45 = -3.333 -> implies slope is > different from 0. But does not mean that slope is > significantly negative, does it? > > so choice has to be A, by elimination. If this is a Schweser question, then they might really mean that the slope coefficient is significant and it is negative therefore, it is significantly negative??? No one will accuse Schweser of clearly wording their questions and answers.

#14

C is the correct answer i made a mistake when i said its not

#15

swaptiongamma Wrote: ------------------------------------------------------- > No way we are dividing here by SEE. Ans has to be > C by the very fact that -1.5/0.45 = -3.333 why do you divide the slope by the std error of the coefficient? shouldn’t you divide the coefficient by its std error?

#16

std error of the coefficient is correct - because the slope = coefficient…

#17

Cmonnnnnnnnnnnnnnn… Audrey! Quant is my strongest area and I knew C has to be the ans.

#18

niraj_a Wrote: ------------------------------------------------------- > swaptiongamma Wrote: > -------------------------------------------------- > ----- > > No way we are dividing here by SEE. Ans has to > be > > C by the very fact that -1.5/0.45 = -3.333 > > > why do you divide the slope by the std error of > the coefficient? shouldn’t you divide the > coefficient by its std error? Slope is the coefficient here!

#19

so .78 is not the coefficient? duly noted from now on: when they say coefficient they mean the slope. i hate my ugrad stats prof for teaching us otherwise.

#20

niraj_a Wrote: ------------------------------------------------------- > so .78 is not the coefficient? > > duly noted from now on: when they say coefficient > they mean the slope. i hate my ugrad stats prof > for teaching us otherwise. 0.78 is the intercept.