Advanced Time Series
Modelling Report
Topics
Your task is to test a hypothesis (see
topics below). You need to discuss the following steps:
(1) data collection (e.g. method of
sampling, data sources, selection criteria);
(2) definition of variables (e.g. control
variables);
(3) model specification (e.g. Unit root,
Cointegration framework; ARCH/GARCH models);
(4) interpretation of findings and
conclusion.
To illustrate your empirical findings, you
are expected to use tables and figures.
Recommended data sources: Datastream,
Bloomberg, OECD Database
Please select one of the following
topics / hypotheses. You are not required to test both hypotheses.
2.1. How does uncertainty affect
sovereign bond yields? One theory is that investors tend to increase their
demand for bonds during periods of higher economic or government policy
uncertainty, thereby increasing their prices and lowering their yields (a
so-called “flight to quality”). Discuss the evidence for or against this
theory, using a variety of governments and time periods.
HINT: You
have various options to address this question. For example, you can examine the
relationship between uncertainty and future bond yields across maturities and
holding periods for the chosen market. You can also examine spillover effects
of uncertainty on bond yields for multiple markets. In your analysis, you can
consider different regimes/periods to test the hypothesis. Make sure to include
necessary control variables (read literature).
VAR framework (VAR and/or VECM) are useful to understand the nature of relationships and co-movement
between the variables. Some example data sources are shown below.
Uncertainty Measure:
World uncertainty index: http://worlduncertaintyindex.com/data/
Macroeconomic uncertainty for the US: https://www.sydneyludvigson.com/macro-and-financial-uncertainty-indexes
Economic Policy Uncertainty: https://www.policyuncertainty.com/
Sovereign Bond Yield Data:
Rich-world sovereign bond yield data is usually
available from a relevant government website. For instance, for US government
bonds, https://www.treasury.gov/resource-center/data-chart-center/interest-rates,
UK
government “gilt” bonds, https://www.bankofengland.co.uk/statistics/yield-curves,
for EU
member states, https://www.ecb.europa.eu/stats/financial_markets_and_interest_rates/long_term_interest_rates/html/index.en.html.
For
sovereigns in emerging markets, try a recognised data source such as Bloomberg
etc.
2.2. Test the following hypothesis:
“There is a strong spillover effect on stock market volatility from the volume
of trading”.
HINT: You
should identify appropriate stock market indices and obtain data on the
corresponding volume of trading from a recognised data source. Use an
appropriate test to establish whether there is a relationship between the two
time series.
Try to use different types of GARCH
models to estimate spillover effects (read literature). Can you identify
any asymmetric pattern? Which model fits the data the best?
Moreover, is the relationship stable over
time? You can consider different regimes/periods to test the hypothesis.
