Scribd
Upload
35 views

Problem Set 2

This document provides the problems for Problem Set II of an Econometrics I course. It includes 5 problems related to simple linear regression modeling. Problem 1 involves estimating a linear regression model to examine the relationship between price and sales of a product across different regions. Problem 2 examines a study on the impact of nap duration on memory test scores. Problem 3 asks how regression results would change if the original variables were transformed. Problem 4 provides data to estimate a wage determination model. Problem 5 asks students to determine if several statements about simple linear regression are true or false.

Uploaded by

Alejandro álvarez Martínez
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
35 views

Problem Set 2

This document provides the problems for Problem Set II of an Econometrics I course. It includes 5 problems related to simple linear regression modeling. Problem 1 involves estimating a linear regression model to examine the relationship between price and sales of a product across different regions. Problem 2 examines a study on the impact of nap duration on memory test scores. Problem 3 asks how regression results would change if the original variables were transformed. Problem 4 provides data to estimate a wage determination model. Problem 5 asks students to determine if several statements about simple linear regression are true or false.

Uploaded by

Alejandro álvarez Martínez
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

School of Economics and Business Administration

University of Navarra
Academic year: 2022/23
Econometrics I
Problem Set II: Ch. 3

NOTE: Please remember that problem sets do not count for the final grade, so it is not
needed to hand in the solutions for this problem set. However, it is highly recommended
trying to solve the questions before the practice class.

PROBLEMS

1. A company assigns different prices to a particular sound equipment in eight different


regions of the country. The following table shows the number of units sold and the
price, in Euro:

Sales 410 400 360 390 420 370 440 420


Price 55 60 65 60 50 65 45 50

(a) Determine the OLS regression line, using the price as the independent variable
(X).
(b) Compute the eight predicted values. Draw them, together with the true val-
ues and the OLS regression line, in a scatter diagram (with the price in the
horizontal axis).
(c) Compute the eight OLS residuals. How can they be represented on the scatter
diagram previously drawn? Compute also the sum of the residuals and the
sum of the residuals squared.
(d) Compute the sum of differences squared between observations and the line
y = 550 − 4x, and compare it with the sum of residuals squared obtained in
part c). Is this result expected?
(e) Let suppose that the model estimated in part a) satisfies all the assumptions
of the simple linear regression model. What is in this case the effect that we
would expect in sales if the price increases by 10 Euro? What is the estimation
of this effect obtained with our eight observations?

2. A researcher runs an experiment to measure the impact of a short nap on memory.


There are 200 participants and they can take a short nap of either 60 minutes or
75 minutes. After waking up, each participant takes a short test for short-term
recall. Each participant is randomly assigned one of the examination times, based
on the flip of a coin. Let Yi denote the number of points scored on the test by
the ith participant (0 ≤ Yi ≤ 100), let Xi denote the amount of time for which
the participant slept prior to taking the test (Xi = 60 or 75), and consider the
regression model Yi = β0 + β1 Xi + ui .

1
(a) Explain what the term ui represents. Why will different participants have
different values of ui ?
(b) What is E(ui | Xi )? Are the estimated coefficients unbiased?
(c) What concerns might the researcher have about ensuring compliance among
participants?
(d) The estimated regression is Yi = 55 + 0.17Xi , with R2 = 0.12 and SER = 3.4.
i. Compute the estimated regression’s prediction for the average score of
participants who slept for 60 minutes before taking the test. Repeat for
75 minutes and 90 minutes.
ii. Compute the estimated gain in score for a participant who is given an
additional 5 minutes to nap.
iii. What is the sample standard deviation of test scores across the 200
participants?

3. A researcher estimates the simple linear regression model: Yi = β0 + β1 Xi + Ui .


Another researcher estimates the same model using the same data but measured
in different units. In particular, Yi∗ = dYi and Xi∗ = cXi , where c and d are two
positive real numbers. Determine the relationship between the results obtained by
both researchers with respect to:

(a) OLS estimators of β0 and β1 .


(b) Residuals.
(c) Standard error.
(d) R2 .
(e) Variance of OLS estimator of β0 .
(f) Variance of OLS estimator of β1 .
(g) Covariance between OLS estimators of β0 and β1 .

4. Consider the model of wage determination:

Yi = β0 + β1 Xi + ui , i = 1, · · · , n

where Yi is salary (measured in Euro) and Xi is the number of years of education.


Let suppose that the estimated model satisfies all the assumptions of the simple
linear regression model, including the homoskedastic one. From a sample of 30
workers we have obtained the following results:
P30 P30 P30
i=1 Xi = 345 i=1Xi2 = 4383 i=1 Xi Yi = 3451.125
P30 P30 2
i=1 Yi = 273 i=1 Yi = 3450.175

2
(a) Compute the OLS estimator of the parameters β0 and β1 . Interpret both
coefficients.
(b) Compute the determination coefficient R2 .
(c) If one worker has exactly 11 years of education, what is the mean and the
variance of her salary? What are the OLS estimators of these values?

5. Analyse whether the following statements are true or false. If they are true, prove
them and if they are false, justify the reason why.

(a) If all the assumptions of the simple linear regression model are satisfied, and
β̂1 is unbiased, then β̂0 is also an unbiased estimator of β0 .
(b) The sample regression line passes through the point (X̄, Ȳ ).
(c) We know that when estimating a simple linear regression model with n obser-
vations, SSR = 10. If we obtain an additional observation and we re-estimate
the model using the n + 1 observations, then we can be sure that the new SSR
obtained will be lower than 10.
(d) A linear regression yields β̂1 = 0 ⇐⇒ R2 = 0.
(e) The R2 coefficient in the regression of Y on X is the value of the sample
correlation between X and Y −→ (R2 = rxy ).

You might also like