Workers used to be able to smoke inside office buildings. Smoking bans were introduced in several areas in the 1990's. Supporters of these bans argue that in addition to elim- inating the externality of secondhand smoke, they would encourage smokers to quit by reducing their opportunities to smoke. In this assignment, you will estimate the effect of workplace smoking bans on smoking, using data in the file Smoking on 10,000 U.S. indoor workers from 1991 to 1993. The data set contains information on whether individuals were or were not subject to a workplace smoking ban, whether the individuals smoked, and other characteristics. A detailed description is given in Smoking_Description.pdf. Report all your regression results in a single table. (a) Estimate the probability of smoking for (i) all workers, (ii) workers affected by smoking bans, and (iii) workers not affected by smoking bans. This can be done using an "if" statement if using Stata, or by separating each group and estimating the model three times. (b) What is the difference in probability of smoking between workers affected by a workplace smoking ban and workers not affected by a ban? Use a linear probability model to determine whether this difference is statistically significant. This means regressing smoker on smkban to determine if the coefficient on smoker is statisti- cally significant. Does your answer agree with your results from part (a)? (c) Estimate a linear probability model with smoker as the dependent variable and the following regressors: smkban, female, age, age, hsdrop, hsgrad, colsome, colgrad, black, and hispanic. Compare the estimated effect of a smoking ban from this regression with your answer from (b). Suggest an explanation, based on the substance of this regression, for the change in the estimated effect of a smoking ban. between (b) and (c). Note: the data set does not have age, you will need to create this variable. If Using Stata, the command is: generate agesq=age age. (d) Test the hypothesis that the coefficient on smkban is zero in the regression from part (c) against the two-sided alternative at the 5% level. (e) Does the probability of smoking increase or decrease with education? Is it statisti- cally significant? (f) Repeat (c)-(e) using a probit model. The Stata command is: probit y 21 22 ... (g) Repeat (c)-(e) using a logit model. The Stata command is: logit y r r2... Ik For the follow parts, it is helpful organize the results in an Excel spreadsheet and calculate the probabilities using simple formulas. Remember to use the cumulative normal distribution for probit results and the logistic for the logit results. i. Suppose you have a white male, non-hispanic, 20-year old, high school drop out. Using the results from the probit regression and assuming that this per- son is not subject to a workplace smoking ban, calculate the probability that this person smokes. What is the effect of the smoking ban on the probability of smoking? ii. Repeat part (i) for a female, black, 40-year old college graduate. iii. Repeat parts (i) and (ii) using the linear probability model. Comment on the differences between the probit, logit, and linear probability results.