class14-06 - Econ 444, Monday November 13, class 14 Econ...

Info iconThis preview shows pages 1–8. Sign up to view the full content.

View Full Document Right Arrow Icon
Econ 444, Monday November 13, class 14 Econ 444, Monday November 13, class 14 Robert de Jong 1 1 Department of Economics Ohio State University Robert de Jong Econ 444, Monday November 13, class 14
Background image of page 1

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

View Full DocumentRight Arrow Icon
Econ 444, Monday November 13, class 14 Class program October 17 Return takehome # 4 Review of Monday’s class New material: F -test Robert de Jong Econ 444, Monday November 13, class 14
Background image of page 2
Econ 444, Monday November 13, class 14 Fourth homework 1 Yes: 22 . 56 > 1 . 96, so reject the null. 2 Yes: 22 . 56 > 2 . 56, so reject the null. 3 t -value < 1 . 96. 4 A little bigger than 5%: 1 . 645 < 1 . 73 < 1 . 96, so between 10% and 5% 5 No: 1 . 73 < 1 . 96, so we cannot reject. 6 No: 1 . 73 < 2 . 56, so we cannot reject. Robert de Jong Econ 444, Monday November 13, class 14
Background image of page 3

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

View Full DocumentRight Arrow Icon
Econ 444, Monday November 13, class 14 Data mining In practice, we need to search for a decent specification Example: in wage equation, do we include geographic dummy variables, sector of employment, education of parents etc.? We should not be searching and searching for the best-looking equation Data mining: searching for the best specification by exhausting all possible equations that can be estimated Data mining in econometrics is a bad thing: this invalidates inference Robert de Jong Econ 444, Monday November 13, class 14
Background image of page 4
Econ 444, Monday November 13, class 14 Recommendation: Try a sensible specification first, and only change it if this is what the data suggest Example: geographic dummy variables are deemed irrelevant: leave them out, and perhaps try a regression with them included to see if they are significant Then if t -values suggest they are relevant, change the original plan Robert de Jong Econ 444, Monday November 13, class 14
Background image of page 5

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

View Full DocumentRight Arrow Icon
Econ 444, Monday November 13, class 14 Olympic games and medals Question: which country did best? Data for: 1 Number of medals for every country in 2004 Olympics 2 GDP per capita for every country 3 Population How do we proceed? Robert de Jong Econ 444, Monday November 13, class 14
Background image of page 6
Econ 444, Monday November 13, class 14 1 What should be our Y i and what should be our X i ? 2
Background image of page 7

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

View Full DocumentRight Arrow Icon
Image of page 8
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 04/13/2009 for the course ECON 444 taught by Professor Ogaki during the Fall '07 term at Ohio State.

Page1 / 20

class14-06 - Econ 444, Monday November 13, class 14 Econ...

This preview shows document pages 1 - 8. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online