{[ promptMessage ]}

Bookmark it

{[ promptMessage ]}

# Lecture4 - Immigration I Lecture 4 Announcements Sketch of...

This preview shows pages 1–9. Sign up to view the full content.

Immigration I Lecture 4, January 31, 2012

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

View Full Document
Announcements Sketch of the next few Friday classes: February 3: Term Paper Session Andrea Williams, Lecturer in Writing Instruction February 10: Term Paper Session Miscellaneous (e.g., Peer Scholar, Q&A, etc.) February 17: Term Paper Session Eveline Houtman, Coordinator of Library Instruction Term Paper: First draft due Friday March 2, 10:00am. 4.5 weeks… And don’t forget to work on the problems. 1
Outline for today Review Estimating the returns to education Training Evaluating Training Programs Immigration Profile of immigration to Canada Immigration policy in Canada Overview of economic questions The impact of immigration Theory Evidence 2

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

View Full Document
Review: Estimating the Returns to Schooling Our focus last week was the estimation of the human capital earnings function: A simplified version is given by: Using the notation from the regression review on Friday, the simple- regression OLS estimator of r is given by: 3 ln W i = β 0 + rS i + β 1 x 1 i + β 2 x 2 i + ... + β k x ki + ε i ln W i = β 0 + rS i + ε i ˆ r = cov(ln W , S ) var( S )
Review: Ability Bias The OLS estimator will be unbiased, unless there is a correlation between S i and the error term, i.e, We include covariates to minimize the risk of omitted variables bias, but this may not be entirely possible. In the case of estimating the returns to education, we are especially concerned about “unobserved ability” that may confound the returns to education and ability. Ability Bias Several different strategies have been employed to address this possibility: Twins studies “Natural Experiments” (or “Instrumental Variables”) Wald Estimator 4 cov( S , ε ) 0

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

View Full Document
Review: Wald Estimator For the simplified model: The Wald Estimator is given by: Where “1” and “2” indicate a partition the sample into two groups such that: 1) , so that the grouping is correlated with the level of schooling; 2) , so that the unobservables are the same (on average) in the two groups. The partition is usually motivated by “natural experiments.” 5 ln W i y i = α + rS i + ε i ˆ r W = y 1 y 2 S 1 S 2 E Δ S 0 E ε 1 [ ] = E ε 2 [ ]
Review: Evidence We discussed evidence on the returns to schooling: Using Canadian Census data Increasing returns over time Trends in Boys’ versus Girls’ schooling decisions Theoretical Models of Training: General Human Capital Specific Human Capital Who pays for the training? How might this be reflected in the returns to job tenure? The wage profile with an employer 6

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

View Full Document
Training Programs Question : Should the government provide job training?
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

### Page1 / 33

Lecture4 - Immigration I Lecture 4 Announcements Sketch of...

This preview shows document pages 1 - 9. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online