The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.
Abstract Details
Activity Number:
|
135
|
Type:
|
Contributed
|
Date/Time:
|
Monday, August 1, 2011 : 8:30 AM to 10:20 AM
|
Sponsor:
|
Business and Economic Statistics Section
|
Abstract - #300752 |
Title:
|
Regime Switching in the Conditional Skewness of S&P 500 Returns
|
Author(s):
|
Mohammad Jahan-Parvar*+ and Bruno Feunou and Romeo Tedongap
|
Companies:
|
East Carolina University and Duke University and Stockholm School of Economics
|
Address:
|
A 426 Brewster Building, Greenville, NC, 27858,
|
Keywords:
|
GARCH ;
Regime Switching ;
Conditional Skewness ;
Volatility ;
Jumps ;
Financial Crisis
|
Abstract:
|
We introduce a simple regime switching GARCH model that captures features of the market returns in normal and crisis episodes better than the symmetric GARCH class, and is considerably easier to implement than Levy-driven models. Hamilton and Susmel (1994) introduce the idea of regime switching in the (G)ARCH literature. We borrow their concept, but apply it to the conditional skewness of returns. Conditional volatility of returns in our model follows a GARCH(1,1) process with Gaussian or Student-t errors, but during crisis episodes the volatility process switches to skewed GED GARCH. This switching happens when conditional skewness of the standardized residuals in the model deviate from near-zero values of a normal GARCH. In normal times, the conditional skewness of returns is practically zero. As a result, symmetric GARCH models are adequate for characterization of returns. On the other hand, during crisis periods, the conditional skewness may significantly deviate from zero. We use daily and monthly S&P500 excess returns for 1970-2010 period. We conduct extensive diagnostic testing for adequacy of the our model which show that it is as good or better than the alternatives.
|
The address information is for the authors that have a + after their name.
Authors who are presenting talks have a * after their name.
Back to the full JSM 2011 program
|
2011 JSM Online Program Home
For information, contact jsm@amstat.org or phone (888) 231-3473.
If you have questions about the Continuing Education program, please contact the Education Department.