tut3_09

# tut3_09 - Show that for appropriate values of ν 1 and ν 2...

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

1 The University of Western Ontario Department of Statistical and Actuarial Sciences SS 3859a Regression Analysis Tutorial 3 Questions: 1. Suppose n observations have been taken on a variable y and on k fixed explanatory variables x 1 , x 2 , . . . , x k . Consider the multiple regression model y ˜ = X β ˜ + ˜ , where ˜ = B z ˜ for an invertible n × n matrix B which has the property B 1 ˜ = 1 ˜ (1 ˜ is the vector of ones), and z ˜ is a vector of n independent standard normal random variables. An intercept is included in the model. The least-squares estimator for β ˜ is given by β ˜ = ( X T B - T B - 1 X ) - 1 X T B - T B - 1 y ˜ (a) Show that β ˜ is an unbiased estimator for β ˜ with variance-covariance matrix given by ( X T B - T B - 1 X ) - 1 . (b) It can be shown that the residual sum of squares is given by SS E = z ˜ T I - B - 1 X X T B - T B - 1 X - 1 X T B - T z ˜ , and under the hypothesis ( H 0 : β 1 = β 2 = · · · = β k = 0, it can be shown that the regression sum of squares is given by SS R = z ˜ T B - 1 X ( X T B - T B - 1 X ) - 1 X T - J /n B - T z ˜ . J is the n ×
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: Show that for appropriate values of ν 1 and ν 2 , SS R /ν 1 SS E /ν 2 has an F-distribution. Iden-tify ν 1 and ν 2 . 2. Suppose { ( x i , y i ) , i = 1 , 2 , . . . , n } are independent observations taken from data gov-erned by the model y = β 1 x + ε where ε is exponentially distributed with parameter 1. Suppose that the x values are all positive. (a) Find the maximum likelihood estimator for β 1 . (b) Estimate β 1 given the following data: x 1 2 3 4 5 y 21 41 60 80 100 (c) Does ε satisfy all of the usual assumptions for linear regression? (d) Bonus: Show that the maximum likelihood estimator for β 1 is biased, and provide an alternative estimator which is unbiased. Also, calculate the variance of the maximum likelihood estimator....
View Full Document

{[ snackBarMessage ]}

### What students are saying

• As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

Kiran Temple University Fox School of Business ‘17, Course Hero Intern

• I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

Dana University of Pennsylvania ‘17, Course Hero Intern

• The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

Jill Tulane University ‘16, Course Hero Intern