Part I: Linear Regression 1. Number of hours worked by working women: Suppose that you want to investigate factors determining the number of hours worked by working women using a multiple linear regression model. Estimate the following two econometric models and answer the questions that follow (use MROZ.sav data). Model I: hours = Bo + Beduc + Bywage + B, exper + BA expersq + B, kidslt6 + Bofaminc + & Model II: hours = Bo + Reduc + Bywage + By exper + BA expersq + Bs kidsIt6 + Bo faminc+ B,huswage- a. Which econometric model is better? b. Report the regression results c. Does the model fit the data very well?| d. What is the importance of including the experience square (expsqr) variable? e. Conduct hypothesis testing for each estimated coefficient. f. Interpret the coefficients.2. A problem of interest to health ofcials (and others) is to determine the effects of smoking during pregnancy on infant health. One measure of infant health is birth weight; a birth weight that is too low can put an infant at risk for contracting various illnesses. Since factors other than cigarette smoking that affect birth weight are likely to be correlated with smoking, we should take those factors into account. For example, higher- income generally results in access to better prenatal care, as well as better nutrition for the mother. An equation that recognizes this is bwghr 2 53 + lcfgs + ,Bzrminc + a. a. What is the most likely sign for 182 ? b. Do you think cfgs and farm inc are likely to be correlated? Explain why the correlation might be positive or negative. c. Now, estimate the equation with and without famine, using the data in BWGHT.sav. Report the results in equation form, including the sample size and Rsquared. Discuss your results, focusing on whether adding famine substantially changes the estimated effect of cfgs on bwghz