determine the significance of the estimate you made in Question 3

1. SkimtheDubin-NollCaltechadmissionsreport.
2. WouldyouconcludethatonlythetotalSATscoresdeterminesadmissionsascomparedtothecomposition?
Hint: Basedon Table 3-11 forinstance,wouldastudent withcombinedSATscoreof1500 (800M700V)bemoreorlesslikelytogainadmission toCaltechasastudentwithacombined scoreof1500(700M800V)? Are there positive or negative effects of having a relatively higher SATV score, and a lower SATM score with the combined SAT score not changed? Show your work!
3. UsingtheresultsinTable3-11 (see PDF of same name on blackboard),howmanymathSATpointswasitworthtobeafemaleapplicant toCaltech) relative to a male applicant (circa1981)? (Hint: Assuming all other variables are constant except gender and SATM, how would the coefficient of male change in the Logit model if male were replaced by female under the usual condition that male+female=1).
4. Usingthesametable, howmanyverbal SATpointswas itworthtobeablackmaleapplicanttoCaltech? Hint: assume that white males are the omitted category in this model. Would you conclude that Hispanic students received a significant admission bump according to this model?
5. How could you determine the significance of the estimate you made in Question 3? Hint: See e.g.http://www.stat.cmu.edu/~hseltman/files/ratio.pdf. What information would you need to know to answer this question?
6. Howcouldadiscretechoicemodelbeusedtoanalyzethetimeofdaythatindividualspicktogotomovies?Howmightamovie theatreusethisinformationtomaximize revenues?