Question

3. Consider estimating the effect of personal computer ownership, as represented by a binary variable, PC, on college GPA, colGPA. With data on SAT scores and high schoool GPA you postulate the model Why might u and PC be positively correlated? If the given equation is estimated by OLS using a random sample of college students, is likelily to have an upward or downward asymptotic bias? Briefly explain why? (c) What are some variables that might be good proxies for the unobservables in u that are correlated with PC? If variable z can be used as a proxy, explain how to conduct an estimation. Are the estimated coefficients consistent?

Answer 1

( 3 )

answer:

a.)

• PC is in all probability decidedly connected with family pay which is excluded in the model

b.)

• If more than one variable is incorporated, at that point the terms in the excluded variable equation include different relapse coefficients, which themselves have the indications of incomplete, not straightforward, correlations..... that implies it's difficult to make sense of what the inclination will be in the coefficients.
• the Best supposition is that it'll be one-sided upward (excessively high) since it'll additionally catch the impacts of the missing factors that are connected with PC.

c.)

Other factors that may be related with PC:

• Family Income
• Understudy Income or student income
• Understudy Loan (binary)... cash to purchase a PC
• Remote Student (binary)... more averse to have a PC.