1. Answer true or false: a. Ordinary least squares generates biased estimates of the parameters in the population regression function Yi = a + BX: + Et If the probability distribution of & is heteroscedastic. b. The variance of the OLS estimator of the variance of b is given by Eel 1 So T-2 E(X,-1)2 provided that E{ &: }=0 and E{ X: Et ]=0. c. The proof of the Gauss-Markov theorem requires that et ~ N(0, OF?). d. The Gauss-Markov theorem states that OLS is the most efficient among all unbiased estimators. 2. a. Why is autocorrelation more commonly observed in time-series data than in cross-sectional data? b. If the distribution of et exhibits positive, first-order autocorrelation, draw a figure showing what you might expect the distribution of the residuals in the population regression against time to look like