The following two equations describe property crime and police expenditures acro
ID: 3207174 • Letter: T
Question
The following two equations describe property crime and police expenditures across U.S. cities:
Crimei = a0 + a1Policei + a2Incomei + u1,i
Policei = b0 + b1Crimei + b2Incomei + b3Liberali + u2,1
Crimei = Number of crimes committed in city i last year
Policei = Total spending on the police force in city i last year
Incomei = Average income in city i last year
Liberali = Share of votes received by the liberal presidential candidate from city i in the last election
a. If you were to estimate these two equations with OLS, would you get consistent estimates? Why or why not?
b. Which of the two equations is fully identified? How do you know this?
c. Describe how you would estimate one or both of the equations using 2SLS. Describe the properties of the estimates in both equations.
(All questions should be solved)
Explanation / Answer
a. These 2 equations are seemingly related regression equation as in regressor of one of the equation becomes predictor for other equation.
Estimates will not be consistent since regressing Y on X is not equal to regressing X on Y. Coefficient for regression
Beta1 for E[Y|X] = Cov(X,Y)/Var(X)
B. Policei equation is fully identified since error u2 term seems to have some fixed value here.
C.We will use SUR (Seemingly unrelated regression) technique to estimate the coefficients together in matrix form. This way the estimates will be efficient.
Related Questions
drjack9650@gmail.com
Navigate
Integrity-first tutoring: explanations and feedback only — we do not complete graded work. Learn more.