ECON301_Handout_03_1213_02

Hence 1 1 t t var a e u 1 1 t t t var a 2 2 1 1 t t t

Info iconThis preview shows pages 10–15. Sign up to view the full content.

View Full Document Right Arrow Icon
Hence, 1 1 ( ) ( ) T t Var a E u 1 1 () T t t Var a  2 2 1 1 T t t Var a Note (and show) that 2 2 1 1 1 T t T t t t a x , so we get: 2 2 2 1 2 1 1 T t T t t t Var a x The importance of this proof is the use of the following property: cov( , ) ( ) 0 u u E u u .
Background image of page 10

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

View Full Document Right Arrow Icon
ECON 301 (01) - Introduction to Econometrics I March, 2012 METU - Department of Economics Instructor: Dr. Ozan ERUYGUR e-mail: [email protected] Lecture Notes 11 3. Mean of 0 In the last lecture, we have established that 01 ˆˆ YX   Substituting 1 1 ˆ T tt t aY we obtain: 0 1 ˆ T t Y X 1 0 1 ˆ T t T t t Y X T Taking t Y as the common factor, we may write: 0 1 1 ˆ T t Xa Y T    Here, denoting 1 Xa b T , we can write the equation as 0 1 ˆ t T t t bY which implies that 0 ˆ is a linear estimator.
Background image of page 11
ECON 301 (01) - Introduction to Econometrics I March, 2012 METU - Department of Economics Instructor: Dr. Ozan ERUYGUR e-mail: [email protected] Lecture Notes 12 Using 01 t t t Y X u  and rearranging yields: 0 0 1 1 ˆ t T tt t b X u   1 0 0 0 1 1 1 1 ˆ t t t T T T t t t b b X bu  Note that 1 1 T t t b and 1 0 T t bX (Show that 1 1 T t t b and 1 0 T t ). Hence the expression reduces to: 00 1 ˆ t T t t Taking expected values of both sides produces 1 ˆ () T t E b E u  By assumption 3 (A3), 0 t Eu . Hence the expression reduces to: 0 ˆ ˆ Mean of E Therefore, in repeated sampling, the mean of OLS estimator 0 ˆ equals to the population regression function’s parameter 0 . We have shown that 0 ˆ is an unbiased estimator of 0 .
Background image of page 12

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

View Full Document Right Arrow Icon
ECON 301 (01) - Introduction to Econometrics I March, 2012 METU - Department of Economics Instructor: Dr. Ozan ERUYGUR e-mail: [email protected] Lecture Notes 13 4. Variance of 0 We established that 00 1 ˆ T tt t bu   The variance of 0 ˆ is given as: 2 0 0 0 ˆ ˆ ˆ ( ) [ ( )] Var E E  or simply: 2 0 0 0 ˆˆ ( ) ( ) Var E Hence: 2 0 1 ˆ ( ) [ ] T t Var E 2 0 1 1 2 2 ( ) ... TT Var E bu b u b u     2 2 2 2 2 2 0 1 1 2 2 1 2 1 2 2 3 2 3 11 ( ) [ ... 2 ( ) 2 ( ) ... 2 ( ) ] Var E b u b u b u bb u u b b u u b b u u other cross terms     Hence, 2 2 2 2 2 2 0 1 1 2 2 1 2 1 2 2 3 2 3 ( ) ( ) ( ) ... ( ) 2 ( ) 2 ( ) ... 2 ( )... Var b E u b E u b E u bb E u u b b E u u b b E u u  
Background image of page 13
ECON 301 (01) - Introduction to Econometrics I March, 2012 METU - Department of Economics Instructor: Dr. Ozan ERUYGUR e-mail: [email protected] Lecture Notes 14 The terms with cross-products of u (cross-terms) will diminish since by assumption 5: ts E(u u ) 0 where st and s,t =1,2,3,…, T . Hence, 22 0 1 ( ) ( ) T tt t Var b E u 2 2 2 2 0 11 () TT Var b b   2 2 0 1 ) 1 ˆ ( T t t Var Xa T      2 2 2 2 0 2 1 2 1 ˆ T t t t Xa Var X a T T Then: 2 2 2 0 12 ˆ X Var a X a    2 2 2 0 ˆ X Var a X a
Background image of page 14

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

View Full Document Right Arrow Icon
Image of page 15
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

Page10 / 20

Hence 1 1 T t Var a E u 1 1 T t t Var a 2 2 1 1 T t t Var a...

This preview shows document pages 10 - 15. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online