Problem 3 The term "redlining" dates to the late 19605. when it was rst used by community activists to describe the practice wherein banks would "draw a red line on a map" to mark an area where they simply refused to grant loansln areas that banks were allegedly redlining. people would nd it difficult to get access to credit. regardless of circumstance or m'oin.can see an example of a map with redlining on it on the following page. where a 1934 map of Austin used by realtors and businesses marks large swathes of East and Soutl Austin |{with predominantly Black and Latinofa residents} as "Hazardous". Through originally coined in the context of bank loans. the term "redlining" has since acquired a broader meaning. and can apply to any denial ofservice based on ethically dubious groundsrace. gender. sexue orientation. and so fortHo financial institution openly admits to redlining. of cteoays a question of whether such practices are happening behind closed doors. with the denial of service then being rationalize in public using other. more socially acceptable reasons. We will now consider a famous example of possible redlining in the insurance industry. from Chicago in the 19?Ds.To measure access to the private home insurance market. we will usel'ezpmber of policies issued by a federpfogram called FAIR.which offers insurance to those who cannot find coverage from private rms.Homeowners are required to carry insurance as a condition for receiving a Ermiltgage. someone wants to buy a house. they must get insurance somewhere. whether through the private market c through FAIR. So the logic here is that the more FAIR policies we see per capita in a ZIP code. the less the residents in that ZIP code are able to turn to the private market. However.private insurance companies can have perfectly reasuna-blisially motivated grounds for denying insurance to peojeme areas of town. for example. are more subject to fire because of nearby industry. mix of building materials. or prevailing wind palal'nsareas have mainly older houses that pose greater liability rislos.individual cases. it is therefore hard to tell whether an insurance company's decision to deny coverage was the result of redlining. or a non-race-based actuarialimle'lai-. we can try to adjust for these ZIP-code differences and look for citywide patterns that might constitute evidence of discrimination. A second issue with this proxy is that it is difcult to tell whether people must turn to a FAIR policy because they are denied coverage outright or because they cannot afford the private coveegeelfferetso have to adjust for differences in income among different areas that might explain differences in FAIR policies. even in the absence of racism. In redline.csv . you are given data on 4'." different ZIP codes in Chihdgwe have is the ZIP-code-level data. rather than data for individual homeowners.) For each ZIP code. you have the following information: . policies : new FAIR plan policies and renewals per 100 housing units in that ZFIQemdmber that more FAIR policies means that residents in that ZIP code are buying private insurance at lower per-capita ratest's our proxy for access to the private market. where more policies implies less access. - minority : percentage of residents in that ZIP code whithe last US censmaelfidentified as a member of racialfethnic minority |li.e. other than no nHispanic white.) - fires: fires per 100 housing units in that ZIP code. . age: percent of housing units in that ZIP code built before WWII - income: median family income in thousands of dollars Use a linear regression moth! assess whether there is an association between the number of FAIR policies and the racialfethic composition of a ZIP cedesting for thefire . age. and incomevariables.Write a short report summarizing your analysis. using the same format you used before [QuestionIApproacthesultsiConclusioiovide confidence intervals where appropriate