Test_1_2002 - θ ω/w and W γ(m v where θ ω m and v...

Info iconThis preview shows page 1. Sign up to view the full content.

View Full Document Right Arrow Icon
Department of Economics Professor Dale J. Poirier University of California, Irvine October 29, 2002 MIDTERM TEST ECON 220A Statistics and Econometrics I (open book) Directions : You must answer each of the following questions. Points (out of 100) are allocated as noted to the left of each question. Allocate your time according to these points. To receive any partial credit, you must show your work. Results from the text need not be reproduced in detail - you can merely cite the source. 1. Let X and Y be continuous random variables with p.d.f. f X,Y (x, y) = (6 - x - y)/8, if 0 < x < 2 and 2 < y < 4, and f X,Y (x, y) = 0, otherwise. (9) (a) Find f X (x). (9) (b) Find f Y|X (y). (9) (c) Find P(2 < Y < 3|X = 1). 2. Suppose Y and W are scalar random variables such that Y|W N(
Background image of page 1
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: θ , ω /w) and W γ (m, v), where θ , ω + , m + , and v + . Answer each of the following questions, fully justifying your answer in each case. (6) (a) Are Y and W independent? (6) (b) Is Y mean-independent of W? (6) (c) Is W mean-independent of Y? (6) (d) Are Y and W uncorrelated? (24) 3. Let Y 1 and Y 2 be random variables with the same variance, but possibly different means. Let Z 1 = Y 1 + Y 2 and Z 2 = Y 1- Y 2 . Find Cov(Z 1 , Z 2 ). (25) 4. Let X and Y be random variables. Define ε = Y - E(Y|X) and U = Y - E*(Y|X), where E(Y|X) is the population regression function and E*(Y|X) is its best linear predictor. Find Cov( ε , U)....
View Full Document

This note was uploaded on 12/12/2010 for the course ECON ECON 220A taught by Professor Dalej.poirier during the Fall '10 term at UC Irvine.

Ask a homework question - tutors are online