Scribd
Upload
24 views2 pages

Tutorial Exercise II

Uploaded by

Lemma Muleta
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
24 views2 pages

Tutorial Exercise II

Uploaded by

Lemma Muleta
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

December 2018

Econ 654: Time Series Econometrics

Tutorial Exercise II: Multivariate Time Series Models


1. Consider the following very simple relationship between aggregate savings St and ag-
gregate income Yt .
St = + Yt + t

For some country this relationship is estimated by OLS over the years 1946 1995
(T = 50). The results are given in Table 1 below:
Table 1: Aggregate savings explained from aggregate income; OLS results
Variable Coefficient Standard error t-ratio
constant 38.900 4.570 8.51
income 0.098 0.009 10.77
T=50 S=22.57 R2=0.93 DW=0.70

Assume, for the moment, that the series St and Yt are stationary.

(a) How would you interpret the coe¢ cient estimate of 0:098 for the income variable?

(b) Explain why the results indicate that there may be a problem of positive autocorre-
lation. Can you give arguments why, in economic models, positive autocorrelation
is more likely than negative autocorrelation?

(c) What are the e¤ects of autocorrelation on the properties of the OLS estimator?
Think about unbiasedness, consistency and the BLUE property.

(d) Describe two di¤erent approaches to handle the autocorrelation problem in the
above case. Which one would you prefer?

From now on, assume that St and Yt are nonstationary I (1) series.

(e) Are there indications that the relationship between the two variables is ‘spurious’?

(f) Explain what we mean by ‘spurious regressions’.

(g) Are there indications that there is a cointegrating relationship between St and Yt ?

1
(h) Explain what we mean by a ‘cointegrating relationship’.

(i) Describe two di¤erent tests that can be used to test the null hypothesis that St

and Yt are not cointegrated.

(j) How do you interpret the coe¢ cient estimate of 0:098 under the hypothesis that
St and Yt are cointegrated?

(k) Are there reasons to correct for autocorrelation in the error term when we estimate
a cointegrating regression?

(l) Explain intuitively why the estimator for a cointegrating parameter is super con-
sistent.

(m) Assuming that St and Yt are cointegrated, describe what we mean by an error-
correction mechanism. Give an example. What do we learn from it?

(n) How can we consistently estimate an error-correction model?

2. In the …les INCOME we …nd quarterly data on UK nominal consumption and income,
for 1971 : 1 to 1985 : 2 (T = 58).

(a) Test for a unit root in the consumption series using several augmented Dickey–
Fuller tests.

(b) Perform a regression by OLS explaining consumption from income. Test for coin-
tegration using two di¤erent tests.

(c) Perform a regression by OLS explaining income from consumption. Test for coin-
tegration.

(d) Compare the estimation results and R2 ’s from the last two regressions.

(e) Determine the error-correction term from one of the two regressions and estimate
an error-correction model for the change in consumption. Test whether the ad-
justment coe¢ cient is zero.

(f) Repeat the last question for the change in income. What do you conclude?

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy