{[ promptMessage ]}

Bookmark it

{[ promptMessage ]}

Lecture 21 Multiple linear IV model and 2-stage least squares

Lecture 21 Multiple linear IV model and 2-stage least squares

Info icon This preview shows pages 1–5. Sign up to view the full content.

View Full Document Right Arrow Icon
Economics 326 Methods of Empirical Research in Economics Lecture 21: Multiple linear IV model and two-stage least squares (2SLS) Vadim Marmer University of British Columbia May 5, 2010
Image of page 1

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

View Full Document Right Arrow Icon
Multiple linear IV model I In empirical research, we often have to estimate models that include multiple endogenous and exogenous regressors. I Example: ln Wage i = γ 0 + γ 1 Age i + γ 2 Sex i + β 1 Educ i + β 2 Children i + U i . I Exogenous regressors: age, sex, and a constant. I Endogenous regressors: education and children (family size). 1/11
Image of page 2
Multiple linear IV model I Consider the following model: y i = γ 0 + γ 1 X 1 , i + . . . + γ k X k , i + β 1 Y 1 , i + . . . + β m Y m , i + U i , where I y i is the dependent variable. I γ 0 is the coe¢ cient on the constant regressor: EU i = 0 . I X 1 , i , . . . , X k , i are the k exogenous regressors: Cov ( X 1 , i , U i ) = . . . = Cov ( X k , i , U i ) = 0 . I Y 1 , i , . . . , Y m , i are the m endogenous regressors: Cov ( Y 1 , i , U i ) 6 = 0 , . . . , Cov ( Y k , i , U i ) 6 = 0 . 2/11
Image of page 3

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

View Full Document Right Arrow Icon
Identi°cation problem I There are k + 1 + m unknown coe¢ cients y i = γ 0 + γ 1 X 1 , i + . . . + γ k X k , i + β 1 Y 1 , i + . . . + β m Y m , i + U i . I The exogeneity conditions EU i = 0 and Cov ( X 1 , i , U i ) = . . . = Cov ( X k , i , U i ) = 0 give us only k + 1 equations: E [ y i ° γ 0 ° γ 1 X 1 , i ° . . . ° γ k X k , i ° β 1 Y 1 , i ° . . . ° β m Y m , i ] = 0 , E [ X 1 , i ( y i ° γ 0 ° γ 1 X 1 , i ° . . . ° γ k X k , i ° β 1 Y 1 , i ° . . . ° β m Y m , i )] = 0 , . . . E [ X k , i ( y i ° γ 0 ° γ 1 X 1 , i ° . . . ° γ k X k , i ° β 1 Y 1 , i ° . . . ° β m Y m , i )] = 0 . I There are more unknowns than equations. Thus, the knowledge of the true covariances between X ±s, Y ±s and y is not su¢ cient to recover the unknown coe¢ cients γ 0 , γ 1 , . . . , γ k , β 1 , . . . , β m .
Image of page 4
Image of page 5
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

What students are saying

  • Left Quote Icon

    As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

    Student Picture

    Kiran Temple University Fox School of Business ‘17, Course Hero Intern

  • Left Quote Icon

    I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

    Student Picture

    Dana University of Pennsylvania ‘17, Course Hero Intern

  • Left Quote Icon

    The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

    Student Picture

    Jill Tulane University ‘16, Course Hero Intern