Sample Exam Questions for Econometrics
1
a)
What is meant by marginalisation and conditioning in the process of
model reduction within the dynamic modelling tradition? (30%)
b)
Having derived a model for the exchange rate s
t
as a function of the
interest rate differential r
t
and performed the following regression.
s
t
= a + b r
t
+ e
t
Where e
t
is an error term. How would you check for the presence of
serial correlation in the error term and how would you deal with it. (30%)
c)
Explain what recursive estimation is and how it would be used to assess
the stability of this equation. (40%)
2
a)
Define the term’s weak stationarity, Integrated of order one and uniform
mixing. How would you asses the stationarity of a variable X.(30%)
b) Suppose X was the US stock market index and your data period was
from 19201938 (to include the stock market crash). How would the testing
procedure for stationarity be affected? (30%)
c) If both the Dollar/Sterling exchange rate (E) and the Yen/Dollar
exchange rate (Y) were I (1) but there was in fact no relationship between
the two variables, what would you expect the result would be of performing
the following regression. (40%)
E
t
=a + bY
t
+v
t
3
Suppose both X and Y are I(1) variables which are generated by the
following true system
X
t
=a+bY
t
+e
t
Y
t
=Y
t1
+v
t
Where e and v are stationary error processes.
This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
a)
Define the common stochastic trend underlying this model (20%)
b)
What is the cointegrating vector(20%)
c)
Explain the relationship between the number of cointegrating vectors in
a system and the number of stochastic trends.(20%)
d) What is the importance of the Granger Representation theorem to
practical modelling?(40%)
4
Suppose we are estimating a model for the return on a bond r
t
of the form,
r
t
=a + br
t1
+ e
t
where e is an error term.
This is the end of the preview.
Sign up
to
access the rest of the document.
 Fall '07
 Francisco
 Econometrics, Regression Analysis, Variance, Autocorrelation, Stationary process

Click to edit the document details