Unformatted text preview: (b) First regress Y i onto X i and obtain residuals e i . Then regress e i onto e i-1 and obtain ˆ ρ . Finally, regress Y * i = Y i-ˆ ρY i-1 onto X * i = X i-ˆ ρX i-1 to obtain an estimate for the slope coeﬃcient. (c) The diﬀerent does not mean that both estimates are unreliable because the OLS estimator has large variance with serial correlation. The Cochrane-Orcutt method gives an estimator with smaller variance, so the estimate with this method is more reliable than the OLS estimate. 3. (a) False; (b) False; (c) True; (d) False; (e) False; (f) False; (g) False; (h) True; (i) False; (j) True; (l) False; (m) False 1...
View Full Document
- Fall '07
- Econometrics, Null hypothesis, dl