A variable is regressed against three other variables, x, y, and z. Which of the following would NOT be an indication of multicollinearity? X is closely related to: A) 3y + 2z. B) 3. C) 9y, and x is closely related to 4z. D) y2.
y2 (nonlinear relationship). I got that one wrong (I choose 3)
Ans is D. Because x = y2 will be a nonlinear relationhisp
how is x = y2 a non linear relationship… or is that supposed to be read y-squared… then that answer makes sense D
of course…I haven’t studied quant in over a month…so what do i know !
Plotting this function x = y^2 would exhibit a non-linear relationship between x and y
have you been up all night dinesh???
^ I was supposed to, but dunoo when I dozed off in the middle for 3 hrs
What did it…I bet it was corporate governance.
reading55 and those sucked-up questions in QBank … I really got fedup and had to surrender
So X “is related to 3” is an indication of multicollinearity? I guess I don’t know what “is related to” means here (it can’t be correlated to 3), but if it means something like E(X) = 3, that’s not even a regression problem. For instance, X distributed N(mean =3, std. dev. = s) is about as standard issue as regression settings get. x= y^2 is of course also not a problem because it’s now just polynomial regression.
Their explanation was that X would be related to the intercept.
lol. You’re kidding…Tell me you’re kidding…
I would not jest about schweser quant questions
OK well principle #1 - you can’t be collinear with a constant.