91Ó°ÊÓ

$$ \begin{array}{l}{\text { Use the data in LOANAPP for this exercise. The binary variable to be explained is approve, which is }} \\ {\text { equal to one if a mortgage loan to an individual was approved. The key explanatory variable is white, a }} \\ {\text { dummy variable equal to one if the applicant was white. The other applicants in the data set are black }} \\ {\text { and Hispanic. }}\end{array} $$ $$ \begin{array}{c}{\text { To test for discrimination in the mortgage loan market, a linear probability model can be used: }} \\ {\text { approve }=\beta_{0}+\beta_{1} \text { white }+\text { other factors. }}\end{array} $$ $$ \begin{array}{l}{\text { (i) If there is discrimination against minorities, and the appropriate factors have been controlled }} \\ {\text { for, what is the sign of } \beta_{1} ?} \\ {\text { (ii) Regress approve on white and report the results in the usual form. Interpret the coefficient on }} \\\ {\text { white. Is it statistically significant? Is it practically large? }}\end{array} $$ $$ \begin{array}{l}{\text { (iii) As controls, add the variables hrat, obrat, loanpro, unem, male, married, dep, sch, cosign, }} \\ {\text { chist, pubrec, mortlatI, mortlat?, and vr. What happens to the coefficient on white? Is there still }} \\ {\text { evidence of discrimination against nonwhites? }}\end{array} $$ $$ \begin{array}{l}{\text { (iv) Now, allow the effect of race to interact with the variable measuring other obligations as a }} \\ {\text { percentage of income (obrat). Is the interaction term significant? }}\end{array} $$ $$ \begin{array}{l}{\text { (v) Using the model from part (iv), what is the effect of being white on the probability of approval }} \\ {\text { when } o b r a t=32, \text { which is roughly the mean value in the sample? Obtain a } 95 \% \text { confidence }} \\ {\text { interval for this effect. }}\end{array} $$