We use the data in SMOKE to estimate a demand function for daily cigarette consumption. The equation estimated by ordinary least squares, with the usual OLS standard errors in parentheses, is cigs = -3.64 + .880 log(income) - 751 log(cigpric) (24.08) (728) (5.773) -.501 educ + .771 age (.167) 0090 age - 2.83 restaurn (1.11) (160) (.0017) 807, R² 0526. where cigs= number of cigarettes smoked per day. Income annual income. cigpric=the per-pack price of cigarettes (in cents). educ=years of schooling. age=age measured in years. restaurn=a binary indicator equals unity if the person resides in a state with restaurant smoking restrictions. We compute its determination coefficient by computing the auxiliary regression, obtaining a value of R2=0.040. a- Test the first equation for heteroscedasticity at 5% significance level by using Braush- Pagan test. b- Using the feasible GLS procedure based on the equation, the weighted least squares estimates are calculated. Interpret the equation and emphasize the significant differences between these two models. cigs 5.64+ 1.30 log(income)- 2.94 log(cigpric) (17.80) (44) (4.46) -463 educ + 482 age- .0056 age²3.46 restaurn (.0009) (.80) CS CamScanner (20)aran(097) n = 807, R² = .1134.