Question 6 SECTION B Answer three questions from this section. 6. A logit regression model and a Linear Probability Model (LPM are used to explain the mortgage denial rates amongst a random sample of 1234 young families in Britain, 35% of 50,000.The regression results are as follows: denial= 0.0320.103 salary+0.240 minority0.095 deposit 0.0110.052 (0.054 (0.044 (Logit) 0.0220.152 0.024) 0.144 where=cxp(=/1+exp= is the logistic function.The usual standard errors for the Logit model and the robust standard errors for the LPM are reported in parentheses The variable denial equals to 1 if the mortgage application was denied,O otherwise. The variables salaru and depositi are the total annual salary and the downpayment by family i in 10,000.The variable minorityequals to 1 if the applicant belongs to a minority group 0 otherwise (a)5 marks)Describe the estimator underlying the logit model and discuss its properties Note: clearly indicate the likelihood function used, but a detailed dervation of the estimator is not expected. b(5 marks)Discuss the advantages and drawbacks of using the LPM,rather than the logit model, to model the mortgage denial rates c (5 marksDiscuss how you can test the null hypothesis that the ceteris paribus effect of salary on the probability of denial is equal to -0.25. Clearly state the alternative hypothesis, the test statistic, and rejection rule. mortgage denial rate at the mean values of the explanatory variables. Discuss the limitation(s) of the marginal effect obtained and propose an alternative that overcomes such limitations. Note: there is no need to calculate the marginal effect using the alternative approach.