EF308 Assignment 2
Due: 3pm, 26 April 2012
Introduction
This assignment is loosely based on Cheung et al. (2005)
and Molodtsova and Papell (2009) and examines the out-of-
sample predictability of exchange rates.
Methodology
Let st denote the (natrual) log of the spot rate per foreign
currency unit. The forecasting models we consider are of the
form
st+k ?? st = 0 + 1xt + t+k (1)
where k is the forecast horizon and we limit xt to be a single
variable. You will be evaluating and comparing the predic-
tive content of the following xt variables. A variable with an
asterisk is the foreign counterpart of the home variable.
• xt = 0 or 1 = 0. This is the baseline random walk with
drift model (Meese and Rogo , 1983).
• xt = it??it
where it is the home interest rate. If 0 = 0 and
1 = 1, this is the log-linearized version of the uncovered
interest parity condition. This is equation (5) of Cheung et
al. (2005).
• xt = pt ?? pt
?? st where pt is the log home price level. xt
is the (negative) real exchange rate; see equation (1) of
Cheung et al. (2005).
• xt = (mt ?? mt
) ?? (yt ?? y
t ) ?? st where mt is the log home
money supply and yt is the log home income. These are
the variables that determine the equilibrium exchange rate
in macro monetary models; see equation (2) of Cheung et
al. (2005).
• xt = 1:5(t??
t )+0:1(gt??g
t ) where t is the home in
ation
rate and gt is the home output `gap.'' gt is measured as the
percent deviation of real GDP from an estimate of its `po-
tential'' level. This is a simpli ed version of the symmetric
Taylor rule in Molodtsova and Papell (2009).
• xt = 1:5(t ??
t ) + 0:1(gt ?? g
t ) + 0:1(st + pt
?? pt). The
additional term in this Taylor rule is the real exchange rate.
This is the asymmetric Taylor rule in Molodtsova and Pa-
pell (2009).
Data
The data le forex06.csv posted at Moodle contains monthly
data from 1971-01 to 2006-06. The rst line of the data le
contains the names of each column variable. The variable
names are described in the sample code. The home currency is
the U.S. dollar and the foreign currencies are the japanese yen
(jap), canadian dollar (can), swiss franc (sz), british pound
(uk), swedish krona (sw), australian dollar (aus), and danish
krone (den).
Assignment
Each student is assigned one of the four currencies. The as-
signment is to examine and compare the predictive content of
the six variables described above for your assigned currency.
(a) Report and compare the in-sample ts of the model (1)
for the six xt variables for the sample up to 1982-02. Do
this for one-month ahead (k = 1) and one-year ahead
(k = 12) change in the (log) spot exchange rate.
(b) Report and compare the out-of-sample predictability of
the model (1) for the six xt variables and for one-month
ahead (k = 1) and one-year ahead (k = 12) change in the
(log) spot exchange rate. Do this for the pseudo out-of-
sample period after 1982-02 using recursive (expanding
window) and rolling ( xed window) forecasts.
Submission Instructions
Due
The second assignment is due 3pm, 26 April 2012. You must
electronically submit your assignment report via Moodle. No
late assignment reports are accepted without an extenuating
circumstances form. Follow the link in Moodle to submit the
assignment until you get to the Turnitin submit page. From
there, choose `single le upload'' for submission method, type
your name, and for the submission title put in your name.
Your report must be submitted before 3pm of the due date.
The system will not accept submissions after that time. You
should submit your report well in advance of the due time.
Excuses such as `the internet connection was down'' will not
be accepted for missing the due time.
The due time is based on Turnitin''s system clock, not your
computer''s clock. Do not be surprised if the Turnitn clock is
ve minutes ahead of your computer clock. You must submit
your report well in advance of the due time. Turnitin does
not accept submissions after the deadline.
If your submission is accepted by Turnitin, you should re-
ceive a digital receipt by email. Retain this message until
your mark for this course appears on your portal page. If
you did not receive a digital receipt, your submission was not
accepted. Try again. If you still do not get a digital receipt,
email me your report before the due time.
Report Format
Your report must be typeset as an A4-sized document either
inWord (.doc) or .pdf format. The report should begin with a
title section that clearly lists your name, student ID number,
and DCU email address. Without this information, you will
not be credited a mark for this assignment. A project report
template is posted at Moodle; please follow the same format.
Use a reasonable (i.e. legible) font size, line spacing, and
margins. There is no limit or requirement in terms of word
counts or page numbers. However, your report should be
kept short and to the point. Read the questions carefully.
Marks will be deducted for long answers that are not directly
relevant to the question.
Software
You are free to use any software for the assignments. How-
ever, I cannot provide assistance other than the use of R. I
encourage you to at least give R a try; consider this a good
opportunity to learn it. If you nd it too dicult to use, I
recommend that you use either Stata or EViews. Whatever
you decide to use, it is important that you become pro cient
in its use so that you have a tool you can use for your own
data analysis. If you want to install R on your own computer,
read the R Guide.
H.Kawakatsu 1 of 2
Assignment 2, 2012 EF308
General Advice
• Do not include program or code in the main text of the
report. Put all such information in an Appendix with a
smaller xed width font at the end of your report.
• When you report estimation results, do not copy-and-paste
output from the software. Properly format them into tables
or graphs as is done in academic journals. In particular, do
not report too many digits (just because the software prints
them).
• Use tables and gures e ectively. Each table and gure
must be accompanied by a caption or note explaining the
contents of the display (e.g. what are the numbers in paren-
theses?).
• When you quote results from other sources, clearly indicate
the source. For example, there is no need to rederive stan-
dard statistical results in your report; just quote from the
relevant sources. Improper attribution can result in plagia-
rism, equivalent to rst degree murder in academia. In the
text of your report, it is standard to refer to these citations
simply as author (date), e.g. Smith (1992) or Smith (1992,
p.27). Consult Citing & Referencing for further guidance
such as styles for quoting a web site.
• Do not use footnotes or endnotes.
• Do not \decorate" your report. You do not get additional
marks for using fancy fonts, glittering colors, or blinking
images.
References
Cheung, Yin-Wong, Menzie D. Chinn, and Anto-
nio Garcia Pascual, \Empirical Exchange Rate Models
of the Nineties: Are Any Fit to Survive?," Journal of In-
ternational Money and Finance, 2005, 24, 1150{1175.
Meese, Richard A. and Kenneth Rogo , \Empirical Ex-
change Rate Models of the Seventies: Do They Fit Out of
Sample?," Journal of International Economics, 1983, 14,
3{24.
Molodtsova, Tanya and David H. Papell, \Out-of-
sample exchange