Can a multivariate QTARCH combined with technical indicators estimate returns in the commodity futures markets?

Author

Hamelink, Foort ; Vessereau, Thieny

Author_Institution

Dept. HEC, Geneva Univ., Switzerland

fYear

1995

fDate

9-11 Apr 1995

Firstpage

136

Lastpage

140

Abstract

Investigates the ability of a new class of conditional heteroscedasticity threshold models called QTARCH (Qualitative Threshold AutoRegressive Conditional Heteroscedasticity) developed by Gourieroux and Monfort (1992) to estimate conditional returns and variances of futures on commodities. The model is based on information contained in past returns and in technical indicators popular among traders. The methodology is applied to futures on Deutschmark, Sugar, the S&P500 and T-Bill using closing prices. Our results suggest that technical indicators used with a QTARCH methodology can significantly predict future returns and variance

Keywords

commodity trading; finance; forecasting theory; statistical analysis; Deutschmark; S&P500; Sugar; T-Bill; closing prices; commodity futures markets; conditional returns estimation; multivariate QTARCH; prediction; qualitative threshold autoregressive conditional heteroscedasticity; technical indicators; variances; Chaos; Covariance matrix; Linearity; Maximum likelihood detection; Parameter estimation; Predictive models; Statistical analysis; Testing; Vectors; Yttrium;

fLanguage

English

Publisher

ieee

Conference_Titel

Computational Intelligence for Financial Engineering, 1995.,Proceedings of the IEEE/IAFE 1995

Conference_Location

New York, NY

Print_ISBN

0-7803-2145-6

Type

conf

DOI

10.1109/CIFER.1995.495266

Filename

495266