Note: This page is no longer up-to-date. You will be redirected to the NEW web page for Stat 956 within 4 seconds. If you are not sent to that page, please access it via my home page.
This 2007 spring-term graduate course covers those parts of the theory and practice of time series that are of most importance in understanding the price movements of financial assets. This is an active field of research and much of our energy will focus on reasonably recent research articles.
Eventually I will create a web site for Stat 956 that is like the more modern page that I have made for Stat 434. Still, this old-fashoned page can hold the fort for at least a few more months.
I am often asked how this course differs from 434. The ways are many and important:
- Students will engage current research papers which they will be expected to digest, summarize, and --- on occasion --- to go beyond.
- The full range of linear algebra tools will be fair game. Similarly, students will be expected to know about maximum likelihood, efficiency, Bayes's theorem, and to have competence with the asymptotic methods of statistics.
- We will use a wide range of computational tools, and in some cases will will really "look under the hood." It is not expected that students have a background in numerical analysis, but some of the problems that we will require learning about optimization methods and their implementations.
- New for Spring 2007 --- the course will use both S-plus and R. We will spend a decent part of our time on understanding the computational underpinnings of time series models, especially estimation in GARCH models. This is the reason that I have added "and computational statistics" to the course title.
Syllabus
This is is a highly approximate syllabus. The material that we actually cover will depend in good measure on the interests and backgrounds of the participants.
Assignments
This is the key link for our course. The assignments you find here now are those that were used in 2004. You can expect them to change considerably for 2006, but the flavor will be consistent.
Each weekend the assignment for the following week will be posted. There are also links to all earlier assignments, so, as the course progresses, it will be easy for you to see what you have achieved.
Code Fragments
This link contains all of the code fragments that have been (and most that will be) discussed in class.
Resources
Here you will find suggested readings and links to material that is related to our course, though again this is for 2004. This is one of the most active links for our course. In addition to readings, I will add links to many other resources that cover both the cultural and the technical facets of our course.
Software
This is an essential link for you to get started with S-Plus and Finmetrics. I will add further software links as the semester progresses. In particular, we will also work with R, which has the benefit of being free and the drawback of being buggy.
Recreation
All work and no play makes ... well, you get the idea. Check it out when you have time.
BACK TO: J. Michael Steele Home Page