Alternative Models for the Conditional Heteroscedasticity of Stock Returns
This article compares econometric model specifications that have been proposed to explain the commonly observed characteristics of the unconditional distribution of daily stock returns. The empirical results indicate that the most likely ranking is (1) intertemporal dependence models, (2) Student t, (3) generalized mixture-of-normal distributions, (4) Poisson jump, and (5) the stationary normal. Among the intertemporal dependence models for conditional heteroscedasticity, those with a leverage (or asymmetry) effect are superior. The Glosten, Jagannathan, and Runkle specification is the most descriptive for individual stocks, while Nelson's exponential model is the most likely for stock indexes. Copyright 1994 by University of Chicago Press.
When requesting a correction, please mention this item's handle: RePEc:ucp:jnlbus:v:67:y:1994:i:4:p:563-98. See general information about how to correct material in RePEc.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (Journals Division)
If references are entirely missing, you can add them using this form.