... number of factors 1. 17 Consider the following example of multiplying partitioned matrices: A 11 A 21 A12 A22 B 11 B 21 B12 B22 = A 11 B 11 + A12 B 21 A 21 B 11 + A22 B 21 A 11 B12 + A12 B22 A 21 B12 + A22 B22 ... have k1 X= k2 X 11 X 21 X12 X22 n1 n2 with the submatrix X 11 of dimensions n1 × k1 , X12 of dimensions n1 × k2 , X 21 of dimensions n2 × k1 , and X22 of dimensio...
... = X1 β1 + X2 2 + MX y (2. 43) Premultiplying the leftmost and rightmost expressions in (2. 43) by X2 M1 , we obtain ˆ X2 M1 y = X2 M1 X2 2 (2. 44) Copyright c 1999, Russell Davidson and James ... 2 + u; c) P1 y = P1 X2 2 + u; d) PX y = X1 β1 + X2 2 + u; Copyright c 1999, Russell Davidson and James G MacKinnon 2. 8 Exercises 85 e) PX y = X2 2 + u; f) M1 y = X2 2 + u; g) M...
... β2 ∆yt + 3 ∆yt−1 + β4 ∆yt−2 + β5 ∆yt 3 + β6 ∆yt−4 (3. 69) Let γ = ˆ i=2 βi Calculate γ and its standard error in two different ways One method should explicitly use the result (3. 33) , and the ... first-difference model (3. 71), and then, without using the results of (3. 70), rederive the estimates of α, β, γ0 , and γ1 solely on the basis of your results from (3. 71) 3. 23 Simulate...
... values less than 0, and there is a very long right-hand tail For n = Copyright c 1999, Russell Davidson and James G MacKinnon 4. 5 Large-Sample Tests in Linear Regression Models 0 .40 151 f (z) ... Copyright c 1999, Russell Davidson and James G MacKinnon 4. 5 Large-Sample Tests in Linear Regression Models 153 are generated by (4. 47) with β2 = 0, we have that M1 y = M1 u, and...
... (5. 54) As readers are asked to check in Exercise 5. 16, the intervals (5. 53) and (5. 54) are not the same The Vector Case The result (5. 49) can easily be extended to the case in which both θ and ... converges to (5. 35) The above argument shows that (5. 37) tends in probability to (5. 35) Because (5. 37) is asymptotically equivalent to (5. 36), the latter also tends in probability to...
... just (6. 06) Thus the model (6. 06) is a special case of the model (6. 66) Therefore, if (6. 06) is a correctly specified model, that is, if the true DGP is a special case of (6. 06) , then (6. 66) must ... correctly specified model as well, because every DGP in (6. 06) automatically belongs to (6. 66) Since (6. 66) is correctly specified, the standard theory of the linear regression with pred...
... (see Section 7. 6) When we this, H1 becomes (1 − ρL)yt = (1 − ρL)Xt β + εt , (7. 74) (1 − ρL)yt = Xt β + LXt γ + εt (7. 75) and H2 becomes It is evident that in (7. 74), but not in (7. 75), the common ... of the within-groups, or fixed-effects, estimator (7. 85) and Copyright c 1999, Russell Davidson and James G MacKinnon 7. 10 Models for Panel Data 301 the between-groups estimator...
... considered in Section 8. 5, where the null and alternative hypotheses are given by (8. 51) Copyright c 1999, Russell Davidson and James G MacKinnon 8. 8 Bootstrap Tests 341 and (8. 52), respectively ... PW X)−1, ˆ ˆ (8. 88) ˆ ˆ where X ≡ X(β NLIV ), and σ is 1/n times the SSR from IV estimation ˆ of regression (8. 83) Readers may find it instructive to compare (8. 88) with expres...
... McFadden ( 198 9), who seems to have coined the name, and Pakes and Pollard ( 198 9) Other important early papers include Lee and Ingram ( 199 1), Keane ( 199 4), McFadden and Ruud ( 199 4), and Gallant and Tauchen ... i i=1 and a ˆ Q(θ, y) = l−k yi , i=1 Copyright c 199 9, Russell Davidson and James G MacKinnon (9. 91) 9. 5 GMM Estimators for Nonlinear Models 3 79 where...
... c 1999, Russell Davidson and James G MacKinnon 10. 10 Exercises 437 10. 7 Use the result (10. 102) of the preceding exercise to prove the asymptotic information matrix equality (10. 34) 10. 8 Consider ... density (10. 03) with −1 θ = (β20 − 10 ) 10. 3 Generate 10, 000 random samples of sizes 20, 100 , and 500 from the uniform U (0, 1) distribution For each sample, compute γ , t...
... 1999, Russell Davidson and James G MacKinnon 11. 5 Models for Count Data 467 (1985, Chapter 9) and McFadden (1984) For a more up-to-date survey, but one that is relatively superficial, see Maddala and ... forms, by Engle (1984) and Davidson and MacKinnon (1984b) Copyright c 1999, Russell Davidson and James G MacKinnon 454 Discrete and Limited Dependent Variables wher...
... (12. 97) is a demand function, and equation (12. 98) is a supply function In this system, pt and qt denote the price and Copyright c 1999, Russell Davidson and James G MacKinnon 12. 6 Nonlinear Simultaneous ... β• and Σ by using equations (12. 78) and (12. 17), respectively From the results (12. 62) and (12. 63), it is clear that we can estimate the covariance matrix of the...
... Copyright c 1999, Russell Davidson and James G MacKinnon (13. 17) 13. 2 Autoregressive and Moving Average Processes 553 To see this, note that ρ1 L times the right-hand side of equation (13. 17) is the ... c 1999, Russell Davidson and James G MacKinnon (13. 60) 13. 4 Single-Equation Dynamic Models where λ≡ γ0 + γ1 − β1 569 (13. 61) This is the long-run derivative of y ◦ with r...
... hypothesis Dickey-Fuller tests of the null hypothesis that there is a unit root may be based on any of regressions (14. 15), (14. 18), (14. 21), or (14. 22) In practice, regressions (14. 18) and (14. 21) ... c 1999, Russell Davidson and James G MacKinnon (14. 52) 620 Unit Roots and Cointegration where the new parameter α is the short-run multiplier, δ1 = λ2 − 1, and δ2 = (1 − λ2 )...
... is the number of elements of r, and Zt and rt are, respectively, the t th row and t th element of Z and r Copyright c 1999, Russell Davidson and James G MacKinnon 15. 2 Specification Tests Based ... 1999, Russell Davidson and James G MacKinnon 688 Testing the Specification of Econometric Models Nadaraya-Watson estimator and the locally linear estimator For the former, u...