34_BinResp_handout

34_BinResp_handout - Binary response models 73-261...

Info iconThis preview shows pages 1–7. Sign up to view the full content.

View Full Document Right Arrow Icon
Binary response models 73-261 Econometrics November 29 Wooldridge 17.1
Background image of page 1

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

View Full DocumentRight Arrow Icon
p. 2 © CMU / Y. Kryukov 73-261 3.1 Binary response Announcements HW 10 due today at 5:15 pm HW 11 will be posted today due Friday, Dec-3 based on lectures of Nov-22 and today Wednesday – review and final project discussion
Background image of page 2
p. 3 © CMU / Y. Kryukov 73-261 3.1 Binary response Overview Topic 3.1: Binary response Dependent variable is a dummy ( y {0,1} ) e.g. the person is employed or not Estimation: Approach – Logit and Probit functions Method – Maximum Likelihood Estimate (MLE) Interpreting the results: effects, inference Case 3.1.b: Censored response (Tobit) y 0 , and = 0 for some observations Model, MLE estimation, Interpretation
Background image of page 3

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

View Full DocumentRight Arrow Icon
p. 4 © CMU / Y. Kryukov 73-261 3.1 Binary response Regression on employment Y i = 1 if the person is employed, Y i = 0 otherwise X i – education, experience, GPA, etc. Should we estimate y = x ? What about prediction (at x = x 0 )? person will be employed for sure? person will never get a job? We would really prefer to turn into a valid probability (0,1) 5 . 1 ˆ 0 x 5 . 0 ˆ 0 x R ˆ 0 x
Background image of page 4
p. 5 © CMU / Y. Kryukov 73-261 3.1 Binary response Probability functions Want a function G ( z ) that Takes any number z R Turns it into a probability p (0,1) Is increasing in z Answer: . . . . . Logistic (logit): Normal (probit): Actual model: Pr{ y = 1 } = G ( x )   dt z z G z t 2 2 1 2 exp ) ( ) ( )] exp( 1 [ ) exp( ) ( z z z G
Background image of page 5

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

View Full DocumentRight Arrow Icon
p. 6 © CMU / Y. Kryukov
Background image of page 6
Image of page 7
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 01/21/2011 for the course ECON 73261 taught by Professor Kyrkv during the Spring '10 term at Carnegie Mellon.

Page1 / 19

34_BinResp_handout - Binary response models 73-261...

This preview shows document pages 1 - 7. Sign up to view the full document.

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