The Econometric Modelling of Financial Time Series
Now in its second
edition, this is an excellent intermediate-level text on time series analysis
for financial markets. Targeted to academics or theoretically inclined
practitioners, the book offers a scholarly discussion of topics relevant to
financial markets.
Opening chapters
focus on linear ARMA and ARIMA models. Next the book turns to non-linear models,
including stochastic volatility, GARCH, regime switching and bilinear models.
Another chapter explores the use of stable distributions for modeling fat-tailed
return distributions. Linear models discussed in the opening chapters can be
extended to accommodate such distributions. Two chapters explore sophisticated
regression models. A final chapter discussed topics such as long-run
relationships, trends and cycles.
Contents
1. Introduction
2. Univariate linear stochastic models:
basic concepts
3. Univariate linear stochastic models:
further topics
4. Univariate non-linear stochastic
models
5. Modelling return distributions
6. Regression techniques for
non-integrated financial time series
7. Regression techniques for integrated
financial time series
8. Further topics in the analysis of
integrated financial time series
This is not an
elementary book. The writing tends to be succinct, but it is mathematically
rigorous. Discussions focus on univariate time series. Applications are
mentioned, but these tend to be of an academic nature. Don't expect practical
discussions of financial engineering or risk management.
If you have read
Brockwell and Davis (2002) or Enders
(2003), you will be equipped to read
this book. Alexander (2001) is
inadequate preparation. Occasional references to advanced probability or stochastic
calculus make some familiarity with those subjects desirable.
What I like about
this book is the fact that it offers discussions at a level of Hamilton (1994)
or Gourieroux and Monford (1997)
without getting bogged down in econometric topics that lack relevance to
finance. It is more accessible and more practical than Gourieroux and Jasiak (2001).
Topics such as cointegration, martingales, and conditional heteroskedasticity
are discussed in detail. References
to the financial literature abound.
For more books related to time
series analysis, see sections:
.gif)
