CSI 779 / STAT 789
Topics in Computational Statistics:
Computational Finance
Spring, 2001
Wednesdays 4:30 to 7:10.
Instructor:
James
Gentle; email: jgentle@gmu.edu
This course will cover a variety of methods of computational statistics
in the analysis of financial data. Many of the standard results in
finance rely on simplifying assumptions about the distribution of random
components. These results can be examined by Monte Carlo methods, and
can be modified by bootstrapping. The course will address the use of
Monte Carlo and the bootstrap in portfolio optimization and in the
pricing of derivatives. The course will also cover the use of
clustering, classification, and pattern recognition in studying classes
of assets and asset prices.
The emphasis will be on the statistical methods and on the computations,
rather than on topics in the domain of finance. While some background
in finance would be useful, it will not be necessary.
Some knowledge of statistical theory and methods (roughly equivalent
to STAT 554 and STAT 652) and an introduction to computers are
prerequisites.
Texts and References
The content of the course will be based primarily on two monographs:
Fouque, Papanicolaou, and Sircar (2000),
Derivatives in Financial Markets with Stochastic Volatility,
and Michaud (1998) Efficient Asset Management .
Some articles in the current literature will be used.
Notes developed by the instructor will also be distributed.
Links to some useful Web sites will also be provided.
Grading
Performance in the class will be evaluated based on
an in-class midterm (25%)
a final exam consisting of a take-home portion and an in-class
portion (35%)
a project (30%)
a number of smaller assignments (10%)
Students may discuss and otherwise collaborate on the project and the
homework, but what is submitted for grading must
be written by the individual students.
Each student will
prepare a Web page
for presentation of
the project and for some of the smaller assignments.
Topics
- Basics of modern portfolio theory; optimization of quadratic
functions.
- Variations on classical mean-variance optimization; the efficient
frontier under randomness (Michaud).
- Studies of patterns in assets prices; smoothing and pattern
recognition; automating technical analysis.
(Lo, Mamaysky, Wang)
- Does technical analysis work? Empirical studies using automated
procedures of pattern recognition. More general pattern detection.
- Classical Black-Scholes-Merton theory.
- Stochastic volatility and its effects on derivative pricing
(Fouque, Papanicolaou, and Sircar, 2000). Stochastic differential
equations with two sources of randomness.
Schedule
(subject to adjustment)
January 17, 2001
Statistical modeling of financial data.
Methods of computational statistics (handout).
The nature of financial data.
Reference: Rydberg (2000),
International Statistical Review 68, 233--258.
Comparing two distributions; goodness-of-fit tests.
January 24, 2001
Structure in financial data.
Smoothing data.
Reference: Lo, Mamaysky, Wang (2000)
Journal of Finance 55, 1705--1765.
January 31, 2001
Monte Carlo methods in analysis of financial data.
February 7, 2001
Models of Finacial Asset Prices and Portfolio Behavior
February 14, 2001
Discuss semester projects.
Portfolio construction.
Mean-variance optimization.
Quadratic programming.
Software.
The efficient frontier and variations.
Example in Michaud, page 13.
February 21, 2001
Review and summarize some
basics
of financial analysis.
Reference: Sharpe, Alexander, and Bailey (1999)
Investments
February 28, 2001
Discuss semester projects.
More on technical patterns.
More on portfolio optimization.
Variations on classical mean-variance optimization; the efficient
frontier under randomness (Michaud).
Bootstrap methods.
March 7, 2001
No class --- Spring break
March 14, 2001
Midterm exam.
March 21, 2001
Review midterm.
Discuss semester projects.
March 28, 2001
Brief descriptions of semester projects.
Basics of derivatives.
Classical Black-Scholes-Merton theory
(Fouque, Papanicolaou, and Sircar, Chapter 1).
Some basic results in the stochastic calculus
(this will be expanded).
Stochastic volatility and implied volatility
(Fouque, Papanicolaou, and Sircar, Chapter 2).
Assignment.
April 4, 2001
Longer descriptions of semester projects.
Stochastic differential
equations with two sources of randomness.
Stochastic volatility and models for derivative pricing.
(Fouque, Papanicolaou, and Sircar, Chapter 2.)
April 11, 2001
Stochastic volatility and derivative pricing.
Clustering and mean-reverting stochastic volatility
(Fouque, Papanicolaou, and Sircar, Chapter 3).
Applications to pricing of financial derivatives.
(Fouque, Papanicolaou, and Sircar, Chapters 4, 5, and 6).
April 18, 2001
Pricing of American derivatives and other topics
(Fouque, Papanicolaou, and Sircar, Chapter 9).
April 25, 2001
Presentations of semester projects.
Hand out take-home portion of final exam.
May 2, 2001
Take-home portion of final exam due.
In-class portion of final exam.
Students
The students in the class all have homepages on which they put parts
of their assignments and other interesting stuff.
Ben Crain
Yaru Li
Phu Nguyen
Paul Rowane
Xun Wang