iis the observed logged output. Thus, our regression equation isyi=c+°ki+±li+²i+"i:
2

(a) (5 points) First, take log ofY; K; L;and°. Report summary statistics forY; K; L;°;andw.(b) (6 points) Regressyion constant,ki; li;and²i:Test if this function exhibits constant returns toscale.(c) (6 points) In reality, we do not observe²i:Typically a °rm with high productivity shock will usemore input. For the sake of argument, assume that capital is °xed, and thereforekiand²iare notcorrelated.However,liand²iare most likely correlated.Under this circumstance, what wouldhappen if we regressyion constant,ki;andli? Would the parameters be consistently estimated?What would you expect those parameter estimates to be, compared to ones obtained in (b)?(d) (6 points) Regressyion constant,ki;andli:Interpret your result.(e) (5 points) Now consider wagewithat di/ers across locations of °rms. State conditions under whichvariablewworks as an instrument forl:Do you expect those conditions to be satis°ed? Explain.(f) (6 points) Assume those conditions you identi°ed in (e) are satis°ed.Run the IV regression toestimate°and±:Compare your result with the ones obtained in (b) and (d).
3

#### You've reached the end of your free preview.

Want to read all 3 pages?

- Spring '08
- Staff
- Economics, Monopoly, Supply And Demand, li, Yi