slides_Ch2_W[1]

# Melissa tartari yale econometrics 29 93 the ordinary

This preview shows page 1. Sign up to view the full content.

This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: ce: Assume ZCMA but allow E [U ] = λ 6= 0. Show that the moment condition E [(u E (u )) x ] = 0, implied by the ZCMA, is su¢ cient to identify β1 . Derive the implied sample analogue-based MoM estimator of β1 . ˆ MM in equation 2.19? How does it relate to β 1 Melissa Tartari (Yale) Econometrics 28 / 93 The Ordinary Least Squares Approach I Consider …gure 2.4.: we represent 2 data points (x1 , y1 ) and (xi , yi ) for some i of choice. Melissa Tartari (Yale) Econometrics 29 / 93 The Ordinary Least Squares Approach I Consider …gure 2.4.: we represent 2 data points (x1 , y1 ) and (xi , yi ) for some i of choice. ˆ ˆ Let βo and β1 be some value for ( βo , β1 ) - think of these as a guess for the unknown parameters ( βo , β1 ). Melissa Tartari (Yale) Econometrics 29 / 93 The Ordinary Least Squares Approach I Consider …gure 2.4.: we represent 2 data points (x1 , y1 ) and (xi , yi ) for some i of choice. ˆ ˆ Let βo and β1 be some value for ( βo , β1 ) - think of these as a guess for the unknown parameters ( βo , β1 ). Let ui denote the vertical distance between the points (yi , xi ) and ˆ ˆ ˆ βo + β1 xi , xi - what is often called residual : ui = yi ˆ Melissa Tartari (Yale) ˆ βo Econometrics ˆ β1 xi (2.21) 29 / 93 The Ordinary Least Squares Approach I - …gure 2.4 y (xi , yi ) yi ˆˆˆ y = β o + β1 x ˆ ui ˆ yi x1 Melissa Tartari (Yale) ˆˆˆ yi = β o + β1 xi (x1 , y1 ) y1 xi Econometrics x 30 / 93 The Ordinary Least Squares Approach II ˆˆ Suppose we choose βo , β1 to make the sum of the squares of the residuals SSR as small as possible: 1n 2 1n ui , min ˆ ∑ ∑ yi ˆˆ ˆˆ ( βo , β1 ) n i =1 ( βo , β1 ) n i =1 min Melissa Tartari (Yale) Econometrics ˆ βo ˆ β1 xi 2 (2.22) 31 / 93 The Ordinary Least Squares Approach II ˆˆ Suppose we choose βo , β1 to make the sum of the squares of the residuals SSR as small as possible: 1n 2 1n ui , min ˆ ∑ ∑ yi ˆˆ ˆˆ ( βo , β1 ) n i =1 ( βo , β1 ) n i =1 min ˆ βo ˆ β1 xi 2 The FOCs of the optimization problem (2.22) are: 8 ˆˆ &gt; ∂SSR ( βo ,β1 ) = 0 &lt; ˆ ˆ ˆ 2 ∑n=1 yi βo β1 xi = 0 ∂ βo i ) n ˆˆ ˆ ˆ ∂SSR ( βo , β1...
View Full Document

Ask a homework question - tutors are online