Scribd
Upload
32 views2 pages

EC820 Time Series Econometrics: T T+J T T 1 T T+J T

jddkdkdk

Uploaded by

Daniyal Asif
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
32 views2 pages

EC820 Time Series Econometrics: T T+J T T 1 T T+J T

jddkdkdk

Uploaded by

Daniyal Asif
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

Hans-Martin Krolzig Spring Term 2021

EC820 Time Series Econometrics


Assessment: Empirical Project

The Expectations Hypothesis of the Term Structure (EHT) states that the yield rt of a zero bond with a
maturity of T periods equals the mean of the expected one-period interest rates, it+j , plus a potential
risk premium, φt :
T −1
1 X
rt = Et it+j + φt . (1)
T
j=0

The term spread, rt − it , is therefore determined by the expected change in future short-term interest
rates:
T −1
1 X
rt − it = Et ∆j it+j + φt . (2)
T
j=0

Under general conditions, the EHT implies that the spread between it and rt is stationary:

rt − it ∼ I(0). (3)

In other words, while rt and it may be I(1), they should be cointegrated.

Consider yourself hired to investigate the term structure of the country allocated to you (please check
FETS21A Allocation.xlsx):

1. The file FETS21A Data.xlsx on moodle contains for each country monthly time series of:

i : 3M interbank interest rate


r : 10Y government bond yield

The sample period to be analysed commences in 1994 (due to data availability) and ends just
before the Great Reset.

2. Your task is to write a short paper (not longer than ten pages including tables and figures, font
size > 11 pt) investigating if, in the long run, the EHT holds for the country under consideration.
Construct a cointegrated VAR for the short- and long-term interest rate, it and rt , respectively.
Analyse if the series are cointegrated in form of the term spread rt − it . It might be useful to
develop your study along the lines discussed in the computing classes.

3. Important points worth considering in your analysis using EViews include:

• motivation and initial data discussion;


• determine the integration properties of it , rt and rt − it ;
• select an adequate VAR(p) model (with p ≥ 2) of it and rt , discuss its fit and any indications
of misspecification (in the case of error autocorrelation you should revise the model);
• analyse the structural and dynamic properties of the CVAR by testing for Granger Causality
(both directions) and discussing the responses to a shock in it ;
• discuss the roots of the companion matrix and test for the cointegration rank r of the system;
• map the CVAR(p) to a VECM(p − 1) and briefly comment on the resulting model equations.
Hans-Martin Krolzig Spring Term 2021

• identify the cointegration vector β by testing the parametric restrictions implied by the EHT,
and comment on the adjustment coefficients α (if you found that r = 0 proceed here as if
r = 1).
• Finally investigate the robustness of your results when allowing for time-varying volatility:
Re-estimate your selected ECM equation for ∆rt with GARCH(1,1) errors. Do not forget to
check for asymmetries and conditional non-normality. Compare your results to a GARCH
model for ∆rt with a mean equation consisting of a constant only.

Throughout your investigation, discuss the econometric problems involved and present an eco-
nomic interpretation of your findings.

4. Presenting test results etc. in tables and figures can be very useful and can substantially help
your presentation when properly labelled. Tables and figures produced by EViews are of high
quality and can be used (freeze, name, delete irrelevant bits, and save to drive).

5. Marks will be allocated on basis of the demonstrated understanding of the econometric method-
ology, clear presentation and discussion of the results. Aim to be as precise as possible. For
example, when using tests, do not just state the outcome of the test, but discuss the underly-
ing econometric methodology (including test hypotheses and their meaning, test equation, test
statistic etc.). -Your aim should be to discover the features of the time series using the method-
ology introduced in the modules. Be critically of the model. For the quality of your paper, it is
irrelevant whether you find evidence for or against the long-run validity of the EHT. Please note
that this project will prepare for the 2nd part of the final exam. So it is important to understand
what you are doing.

6. Deadline for submitting the project report on moodle via Turnitin:

Friday, 16 Apr 2021, 12:15.

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