2009_ECON0701_tutorial_2_(extra_slides)

# 2009_ECON0701_tutorial_2_(extra_slides) - TO INTERPRET...

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

Unformatted text preview: TO INTERPRET COEFFICIENTS OF DIFFERENT REGRESSION MODELS a) Level-level Model True Model: y 0 1 x E ( y | x) 0 1 x 0 E ( y | x 0) 1 dE ( y | x) dx For 1 unit increase in x, expected y changes by 1 . b) Log-level Model True Model: ln y 0 1 x E (ln y | x) 0 1 x 0 E (ln y | x 0) 1 dE (ln y | x ) dE ( y | x ) / E ( y | x ) %y 100 dx dx x => %y 1001x For 1 unit increase in x, expected y changes by 100 1 %. c) Level-log Model True Model: y 0 1 ln x E ( y | ln x) 0 1 ln x 0 E ( y | ln x 0) 1 dE ( y | ln x ) y y 100 d ln x %x 100 % x y => 1 %x 100 1 For 1 % increase in x, expected y changes by 100 . d) Log-log Model True Model: ln y 0 1 ln x E (ln y | ln x) 0 1 ln x 0 E (ln y | ln x 0) 1 dE (ln y | ln x ) dE ( y | x) / E ( y | x) % y 100 %y d ln x dx / x %x 100 % x For 1 % increase in x, expected y changes by 1 %. Population: Model: y 0 1 x Line: E ( y | x) 0 1 x Sample: Model: y 0 1 x Line: y 0 1 x ...
View Full Document

## This note was uploaded on 09/06/2010 for the course FBE ECON0701 taught by Professor Paul during the Spring '09 term at HKU.

### Page1 / 3

2009_ECON0701_tutorial_2_(extra_slides) - TO INTERPRET...

This preview shows document pages 1 - 3. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online