伍德里奇计量经济学第六章计算机答案,伍德里奇计量经济学第六版答案Appendix-C...

265 APPENDIX C

SOLUTIONS TO PROBLEMS

C.1 (i) This is just a special case of what we covered in the text, with n = 4: E(Y ) = µ and Var(Y ) = σ2/4.

(ii) E(W ) = E(Y 1)/8 + E(Y 2)/8 + E(Y 3)/4 + E(Y 4)/2 = µ[(1/8) + (1/8) + (1/4) + (1/2)] = µ(1 + 1 + 2 + 4)/8 = µ, which shows that W is unbiased. Because the Y i are independent,

Var(W ) = Var(Y 1)/64 + Var(Y 2)/64 + Var(Y 3)/16 + Var(Y 4)/4

= σ2[(1/64) + (1/64) + (4/64) + (16/64)] = σ2(22/64) = σ2(11/32).

(iii) Because 11/32 > 8/32 = 1/4, Var(W ) > Var(Y ) for any σ2 > 0, so Y is preferred to W because each is unbiased.

C.2 (i) E(W a ) = a 1E(Y 1) + a 2E(Y 2) + + a n E(Y n ) = (a 1 + a 2 + + a n )µ. Therefore, we must have a 1 + a 2 + + a n = 1 for unbiasedness.

(ii) Var(W a ) = 21a Var(Y 1) + 22a Var(Y 2) + + 2n a Var(Y n ) = (21a + 22a + + 2n a )σ2.

(iii) From the hint, when a 1 + a 2 + + a n = 1 – the condition needed for unbiasedness of W a

– we have 1/n ≤ 21a + 22a + + 2n a . But then Var(Y ) = σ2/n ≤ σ2(21a

+ 22a + + 2n a ) = Var(W a ).

C.3 (i) E(W 1) = [(n – 1)/n ]E(Y ) = [(n – 1)/n ]µ, and so Bias(W 1) = [(n – 1)/n ]µ – µ = –µ/n . Similarly, E(W 2) = E(Y )/2 = µ/2, and so Bias(W 2) = µ/2 – µ = –µ/2. The bias in W 1 tends to zero as n → ∞, while the bias in W 2 is –µ/2 for all n . This is an important difference.

(ii) plim(W 1) = plim[(n – 1)/n ]⋅plim(Y ) = 1⋅µ = µ. plim(W 2) = plim(Y )/2 = µ/2. Because plim(W 1) = µ and plim(W 2) = µ/2, W 1 is consistent whereas W 2 is inconsistent.

(iii) Var(W 1) = [(n – 1)/n ]2Var(Y ) = [(n – 1)2/n 3]σ2 and Var(W 2) = Var(Y )/4 = σ2/(4n ).

(iv) Because Y is unbiased, its mean squared error is simply its variance. On the other hand, MSE(W 1) = Var(W 1) + [Bias(W 1)]2 = [(n – 1)2/n 3]σ2 + µ2/n 2. When µ = 0, MSE(W 1) = Var(W 1) =

[(n – 1)2/n 3]σ2 < σ2/n = Var(Y ) because (n – 1)/n < 1. Therefore, MSE(W 1) is smaller than Var(Y ) for µ close to zero. For large n , the difference between the two estimators is trivial.

C.4 (i) Using the hint, E(Z |X ) = E(Y /X |X ) = E(Y |X )/X = θX /X = θ. It follows by Property CE.4, the law of iterated expectations, that E(Z ) = E(θ) = θ.