This preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: ÷ ÷ ÷ ÷ ε ε ε X X I O { } 2 2  E Var = . ... ÷ ÷ ÷ ÷ = σ + σ ÷ ÷ X I I ˜˜˜™™ ™ 21/34 Part 6: Finite Sample Properties of LS Variance of the Least Squares Estimator = β ε + ε ε ε = = εε σ β β + β β β 1 1 1 1 1 1 1 2 1 ( ) = ( ) ( ) ( ) E[  ]= ( ) [  ] as [  ] Var[  ] E[( )( ) ' ] ( ) [ ' ] ( ) ( ) ( ) b X'X X'y X'X X' X + = X'X X' b X X'X X'E X = E X b X b b X = X'X X'E X X X'X = X'X X' I X X'X  σ σ σ 2 1 1 2 1 1 2 1 ( ) ( ) ( ) ( ) ( ) = X'X X'I X X'X = X'X X'X X'X = X'X ˜˜˜™ ™ 22/34 Part 6: Finite Sample Properties of LS Variance of the Least Squares Estimator = = σ σ σ β β 1 2 1 2 1 2 1 ( ) E[  ] = Var[  ] ( ) Var[ ] = E{Var[  ] } + Var{E[  ]} = E[( ) ] + Var{ } = E[( ) ] + We will ultimately ne b X'X X'y b X b X X'X b b X b X X'X X'X 1 ed to estimate E[( ) ]. We will use the only information we have, , itself. X'X X ˜˜˜™ ™ 23/34 Part 6: Finite Sample Properties of LS Specification Errors1 Omitting relevant variables: Suppose the correct model is y = X 1 1 + X 2 2 + . I.e., two sets of variables. Compute least squares omitting X 2. Some easily proved results: Var[ b 1] is smaller than Var[ b 1.2]. (The latter is the northwest submatrix of the full covariance matrix. The proof uses the residual maker (again!). I.e., you get a smaller variance when you omit X 2. (One interpretation: Omitting X 2 amounts to using extra information ( 2 = ). Even if the information is wrong (see the next result), it reduces the variance. (This is an important result.) ˜˜˜™ ™ 24/34 Part 6: Finite Sample Properties of LS Omitted Variables (No free lunch) E[ b 1] = 1 + ( X1X1 ) 1X1X2 2 1. So, b 1 is biased .(!!!) The bias can be huge. Can reverse the sign of a price coefficient in a “demand equation.” b 1 may be more “precise.” Precision = Mean squared error = variance + squared bias....
View
Full Document
 Fall '10
 H.Bierens
 Econometrics, Least Squares, Standard Deviation, Variance, Mean squared error, Bias of an estimator

Click to edit the document details