This preview shows pages 1–3. Sign up to view the full content.
This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: Economics 4261 Introduction to Econometrics Fall 2010 HOMEWORK 2 : SIMPLE LINEAR REGRESSION Question 1 Consider two random variables X and Y , such that p X,Y q is distributed bivariate normal. Suppose X 2 . 7 , Y 3. Further, X . 36 and Y . 25. The correlation between X and Y is . 8. (a) How is X Y distributed? (b) Calculate Pr p X Y 0. (c) Calculate Pr p Y 3 . 3  X 3 q .................................................................................................................. (a) X Y N X Y , 2 X 2 X Y 2 Y Hence, X Y N . 3 , . 36 2 2 p . 8 qp . 36 qp . 25 q . 25 2 . (b) This is a righttailed test. Since X Y N r . 3 , . 0481 s , it follows that Z . 3 ? . 0481 1 . 368 . The pvalue for the onesided test is 0 . 0857. Thus, the probability is 8 . 57%. (c) First we need Y  X x , which is given by Y  X x N Y Y X p x X q , 2 Y p 1 2 q . Plugging in the numbers, we find, Y  X 3 N 2 . 7 . 8 . 25 . 36 p 3 2 . 7 q , . 25 2 p 1 . 64 q , or, Y  X 3 N r 3 . 1 6 , . 0225 s . The ztest is z 3 . 3 3 . 1 6 ? . 0225 . 889 . This is also a righttailed test, where p . 8133, so the answer is 1 . 8133 . 187, or 18 . 7%. kwilliams@umn.edu http://www.econ.umn.edu/ ~ will3324 Page 1 of 9 Economics 4261 Introduction to Econometrics Fall 2010 Question 2 Suppose the pdf for p X,Y q is given by f p x,y q : p x y q{ 3 for 0 x 1 and 0 y 2, and f p x,y q : 0 otherwise. (a) Verify this is a valid pdf. (b) What is the marginal density with respect to Y ? (c) Find Pr p X 2 Y q . (d) What is E r X  Y 1 s ? .................................................................................................................. (a) We just need to verify that the pdf integrates to unity. The cdf is given by X Y x 3 y 3 dy dx. Thus our proposed candidate is, F p x,y q : x 2 y 6 xy 2 6 , for p x,y q P r , 1 s r , 2 s . Clearly F p , q 0. Also, note that F r 1 , 2 s 1 { 3 2 { 3 1. We are good to go. (b) To obtain the marginal distribution with respect to Y , we integrate over X . g p y q X f p x,y q dx 1 x 3 y 3 dx x 2 6 xy 3 1 2 y 1 6 for y P r , 2 s . (c) To solve this question, it might be beneficial to draw a rectangle and see that Pr p X 2 Y q 1 1 2 x f p x,y q dy dx 1 1 2 x x 3 y 3 dy dx 1 xy 3 y 2 6 1 2 x dx 1 x 2 6 x 2 24 dx x 3 18 1 x 3 73 1 1 18 1 72 4 72 1 72 5 72 ....
View
Full
Document
This note was uploaded on 02/24/2011 for the course ECON 4261 taught by Professor Staff during the Spring '08 term at Minnesota.
 Spring '08
 Staff
 Econometrics

Click to edit the document details