PanelDataNotes-4-MDE

# PanelDataNotes-4-MDE - Econometric Analysis of Panel Data...

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

Econometric Analysis of Panel Data William Greene Department of Economics Stern School of Business

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

View Full Document
Econometric Analysis of Panel Data 4-A. Minimum Distance Estimation
Chamberlain’s Model Chamberlain (1984) “Panel Data,” Handbook of  Econometrics Innovation: treat the panel as a system of equations:  SUR Models, See Wooldridge, Ch. 7 through p. 172. Assumptions: Balanced panel Minimal restrictions on variances and covariances of  disturbances (zero means, finite fourth moments) Model the correlation between effects and regressors

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

View Full Document
Chamberlain (2) it i it i i i i y , each observation   , T observations for individual i Assuming no time invariant variables in  . (To be picked up when we examine Hausman and Taylor.) Re: Mundlak's treatment = α + + ε = α + + it i x β y i X β ε X i T i 0 t 1 i i i , E( | ) 0. w Not a regression. Changes with next period's data.  Viewed as the   of   on  (1, , ,,. .., ) . = α α = α + Σ + ′ ′ α = i it t i1 i2 iT X x δ projection x x x x
Chamberlain (3) - Data 11 12 1T 11 12 1T                        Period                      Period                    t=  1     2  . ..    T          1     2  . ..    T Individual i=1    y   y   . ..  y                . ..   Individual x x x 21 22 2T 21 22 2T 11 12 1T 11 12 1T  i=2    y   y   .                  . ..                . ..                            . .. Individual i=N    y   y   .          x x x x x x it it i i                       y                       K variables                         T variables           = TK variables                           = NxT matrix           = N x TK matrix = = x y x Y X

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

View Full Document
Chamberlain (4) Model = = = α + + ε ε = ε ε = ϖ α = α + Σ + = α + Σ + + ε + α + + = = ϖ σ σ π it i it it i it is i ts T i 0 t 1 i T it 0 t 1 it i 2 0 i t it it i it is i ts w 2 w y ,  E[ | ] 0,  E[ | ]  unrestricted w y w     =  v ,  E[v | ] 0,  E[v v | ] +  still unrestricted =    is a it it t it t it x x x β x δ x x δ β x x x     I Σ Ω = α + + = α + + π π i1 0 i 1 i2 0 i 2 i2 n unrestricted TxT covariance matrix. SEEMINGLY UNRELATED REGRESSIONS y v     Equation uses year 1 data, N observations y v    Each equation has y for that year regressed on     . . x x = α + + π iT 0 i T iT .                       the x's from all years.  There is a constant term y v    plus TxK variables in each equation. x
Chamberlain (5) SUR Model = α + + = α + + = α + + α α α α + + π π π π π π Π i1 0 i 1 i2 0 i 2 i2 iT 0 i T iT 0 0 0 0 i2 iT i i2 iT 1 2 T i i i The SUR system y v ,    y v   . ..,   Arranged in a row now

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.

## This note was uploaded on 01/05/2012 for the course B 55.9912 taught by Professor Willamgreene during the Fall '11 term at NYU.

### Page1 / 33

PanelDataNotes-4-MDE - Econometric Analysis of Panel Data...

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

View Full Document
Ask a homework question - tutors are online