Scribd
Upload
247 views

Homework Chapter 9: More On Specification and Data Issues: Econ 30331: Econometrics Prof. Byung-Joo Lee

1. When additional quadratic terms for CEO and company tenure are added to the CEO salary model, the R-squared increases, suggesting there may be functional form misspecification in the original model. 2. Adding the percentage of students eligible for free lunch (a proxy for poverty) substantially increases the R-squared and lowers the effect of expenditures on math test scores, though expenditures still have a statistically significant effect. The addition of the proxy variable also suggests pass rates are lower for schools with higher poverty and enrollment. 3. Applying the Ramsey RESET test by adding squared and cubed terms of the fitted values to a CEO salary model including sales, return on equity, and a dummy for

Uploaded by

k
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
247 views

Homework Chapter 9: More On Specification and Data Issues: Econ 30331: Econometrics Prof. Byung-Joo Lee

1. When additional quadratic terms for CEO and company tenure are added to the CEO salary model, the R-squared increases, suggesting there may be functional form misspecification in the original model. 2. Adding the percentage of students eligible for free lunch (a proxy for poverty) substantially increases the R-squared and lowers the effect of expenditures on math test scores, though expenditures still have a statistically significant effect. The addition of the proxy variable also suggests pass rates are lower for schools with higher poverty and enrollment. 3. Applying the Ramsey RESET test by adding squared and cubed terms of the fitted values to a CEO salary model including sales, return on equity, and a dummy for

Uploaded by

k
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

Homework Chapter 9: More on Specification and Data

Issues
Econ 30331: Econometrics Prof. Byung-Joo Lee

1. Using the data in CEOSAL2.dta, the following model is estimated:

log(salary) = β0 + β1 log(sales) + β2 log(mktval) + β3 prof marg


+β4 ceoten + β5 comten + u

with R2 = .353 (n = 177). When ceoten2 and comten2 are added, R2 = .375. Is
there evidence of functional form misspecification in this model?

2. Let math10 denote the percentage of students at a Michigan high school receiving a
passing score on a standardized math test (see also Example4.2). We are interested
in estimating the effect of per student spending on math performance. A simple
model is

math10 = β0 + β1 log(expend) + β2 log(enroll) + β3 poverty + u

where poverty is the percentage of students living in poverty.


(a) The variable lnchprg is the percentage of students eligible for the feder-
ally funded school lunch program. Why is this a sensible proxy variable
for poverty?
(b) The table that follows contains OLS estimates, with and without lnchprg as
an explanatory variable.

Dependent Variable: math10


Independent Variables (1) (2)
log(expend) 11.13 7.75
(3.30) (3.04)
log(enroll) 0.022 -1.26
(.615) (.58)
lnchprg - -0.324
(.036)
intercept -69.24 -23.14
(26.72) (24.99)
Observations 428 428
R-square 0.0297 0.1893

Explain why the effect of expenditures on math10 is lower in column (2) than
in column (1). Is the effect in column (2) still statistically greater than zero?
(c) Does it appear that pass rates are lower at larger schools, other factors being
equal? Explain.
(d) Interpret the coefficient on lnchprg in column (2).
(e) What do you make of the substantial increase in R2 from column (1) to
column (2)?

15
3. Use CEOSAL1.dta to estimate the following CEO salary equation:

log (salary) = β0 + β1 log (sales) + β2 roe + β3 rosneg + u

where rosneg is a dummy variable equal to one if ros < 0 and equal to zero if
ros ≥ 0. Generate dummy variable rosneg using Stata command gene rosneg =
(ros < 0). Apply RESET test by adding ŷ 2 and ŷ 3 to the above regression equation
to test the functional form misspecification of the original regression equation.

4. Use the data set WAGE2.dta to estimate the following model:

log (wage) = β0 + β1 educ + β2 exper + β3 tenure + β4 married + β5 south


+ β6 urban + β7 black + β8 IQ + u

(a) Use the variable KW W (the "knowledge of the world of work" test score) as
a proxy for ability in place of IQ. What is the estimated return to education
in this case?
(b) Now, use IQ and KW W together as proxy variables. What happens to the
estimated return to education?
(c) In part (b), are IQ and KW W individuall significant? Are they jointly
significant?

16

You might also like