GARCH TIME-SERIES MODELS: AN APPLICATION TO RETAIL LIVESTOCK PRICES

This article applies recent developments in time-series modeling to analyze the retail prices of beef, pork, and chicken. Specifically, generalized autoregressive conditional heteroscedasticity (GARCH) models were fitted to these data to determine if, unlike more traditional time-series models, the conditional variances of the underlying stochastic processes are nonconstant. The estimation results indicate that the constant conditional variances assumption can be rejected. Furthermore, ex post forecast intervals generated from the GARCH processes indicate that the forecasting accuracy of the estimated models has varied widely over time with substantial volatility occurring during the 1970s and early 1980s.


Issue Date:
1988-12
Publication Type:
Journal Article
PURL Identifier:
http://purl.umn.edu/32111
Published in:
Western Journal of Agricultural Economics, Volume 13, Number 2
Page range:
365-374
Total Pages:
10




 Record created 2017-04-01, last modified 2017-08-24

Fulltext:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)