Lahore School of Economics MPHIL Econometrics I (Winter 2010) Problem Set 1-Q4-Solutions

# Lahore School of Economics MPHIL Econometrics I (Winter 2010) Problem Set 1-Q4-Solutions

This preview shows pages 1–2. Sign up to view the full content.

Mphil Advanced Econometrics Solution to Problem Set no 1 Q4.In regression model the variable y is regressed on the variable x with resulting regression line a+bx. Reversing the role of the two variables , x can be regressed on y with the resulting regression line c+dy. a. Derive formulas for the least squares estimates of c and d obtained by regressing x on y. b. Show that bd=R 2 , where b is the conventional least squares estimator and d the slope estimator in a. c. Conclude that in general d≠1/b. Explain this in terms of the criterion functions used to obtain b and d.

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: Answer: a. X=c+dy S(c,d)= Ʃ (Xi-c-dy) 2 Ʃ (Xi-c-dy)=0 Ʃ (Xi-c-dy)=0 d= (x Ʃ i-)(y i-)/ ( Ʃ y i-) 2 b. b.d = (x Ʃ i-)(y i-)/ ( Ʃ y i-) 2 . (x Ʃ i-)(y i-)/ ( Ʃ x i-) 2 Now given that y i= a+bx i +e i Since a= Ʃ (y i-)=b 2 (x Ʃ i-) 2 + e Ʃ i 2 since (x Ʃ i-) 2 e i =0 Ʃ (y i-)=b 2 (x Ʃ i-) 2 + e Ʃ i 2 SST=b(SSE)+SSR R 2 =SSE/SST=b 2 (x Ʃ i-) 2 / ( Ʃ y i-) 2 Now b= (x Ʃ i-)(y i-)/ ( Ʃ x i-) 2 R 2 = (x Ʃ i-)(y i-)/ ( Ʃ x i-) 2 ( Ʃ y i-) 2 =bd<= thus prooved Mphil Advanced Econometrics Solution to Problem Set no 1...
View Full Document

## This note was uploaded on 03/23/2012 for the course ECON 201 taught by Professor Cowell during the Spring '10 term at LSE.

### Page1 / 2

Lahore School of Economics MPHIL Econometrics I (Winter 2010) Problem Set 1-Q4-Solutions

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online