Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd
Upload
32 views

Problems

1. The document presents data and equations for estimating parameters α and β in a simple linear regression model using ordinary least squares. 2. It provides estimates and standard errors for coefficients in several regression models and asks to conduct hypothesis tests on the coefficient values. 3. Questions are asked about elasticities in a production function, returns to scale, and the significance of coefficients in another regression model. 4. A theoretical production function is presented and it is shown that if a firm maximizes profits, the log of managerial input will be linearly related to logs of other variables. The potential issue with estimating a misspecified version of this production is discussed.

Uploaded by

kebede desalegn
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
32 views

Problems

1. The document presents data and equations for estimating parameters α and β in a simple linear regression model using ordinary least squares. 2. It provides estimates and standard errors for coefficients in several regression models and asks to conduct hypothesis tests on the coefficient values. 3. Questions are asked about elasticities in a production function, returns to scale, and the significance of coefficients in another regression model. 4. A theoretical production function is presented and it is shown that if a firm maximizes profits, the log of managerial input will be linearly related to logs of other variables. The potential issue with estimating a misspecified version of this production is discussed.

Uploaded by

kebede desalegn
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

1.

A Sample of 20 observations corresponding to the model


yi = α + βxi + ui
gave the following data:
X X X
yi = 21.9 (yi − ȳ) = 86.9 (xi − x̄)(yi − ȳ) = 106.4
X X
2
xi = 186.2 (xi − x̄) = 215.4

Estimate α and β by OLS.

2. Consider the following regression


colĜP A = 1.39 + 0.412hsGP A + 0.015ACT − 0.083skipped
(0.33) (0.094) (0.011) (0.026)
2
n = 141, R = 0.234
a) Using the standard normal approximation, find the 95% confidence inter-
val for β hsGP A .
b) Can you reject the hypothesis H0 :β hsGP A = 0.4 against H1 :β hsGP A 6= 0.4.
c) Can you reject the hypothesis H0 :β hsGP A = 1 against H1 :β hsGP A 6= 1.

3. The following equation is estimated as a production function for Q:


ln Q = 1.37 + 0.632 ln K + 0.452 ln L
(0.257) (0.219)
2
R = 0.98 cov(bk , bl ) = 0.055
where the standard errors for bk and bl are given in parentheses. Test the
following hypotheses:
a) The capital and labor elasticities of output are identical.
b) There are constant returns of scale.

4. The following estimated equation was obtained by ordinary least squares


using quarterly data for 1971 to 1976 inclusive
Yt = 1.10 − 0.0096X1t − 4.56X2t + 0.0345X3t
(2.12) (0.0034) (3.35) (0.007)
The numbers inside the brackets are estimated standard errors.
Explained sum of squares = 109.24 and Residual sum of squares = 20.22.
a) Test the significance of each of the slope coefficients.
b) Calculate the coefficient of determination R2 .
c) Test the overall significance of the regression.

5. A firm has a production function:


Y = AK α Lβ M γ eu

1
where Y is the output, K is capital, L is labour, M is managerial input
and u is a random disturbance. At fixed levels of K and L, and given fixed
prices, py and pm , for output and managerial services, show that if the firm
maximizes profits (i.e. chooses M such that pm is equal to the value of the
marginal product of M ), the following relationship holds:

1 py α β
lnM = constant + ln + ln K + ln L + error.
1 − γ pm 1 − γ 1−γ
Suppose now that an econometrician estimates the following misspecified pro-
duction function:
ln Yi = a0 + a1 ln Ki + a2 ln Li + vi
by least squares for a cross section sample of such firms, and estimates the
degree of returns-to-scale in the industry by

r̂ = â1 + â2 .

What would you expect about the estimator r̂?

You might also like