Template-Type: ReDIF-Paper 1.0
Series: Tinbergen Institute Discussion Papers
Creation-Date: 1998-09-28
Number: 98-104/2
Author-Name: Patrick A. Groenendijk
Author-Email: pgroenendijk@feweb.vu.nl
Author-Workplace-Name: Vrije Universiteit Amsterdam
Author-Name: André Lucas
Author-Email: alucas@feweb.vu.nl
Author-Workplace-Name: Vrije Universiteit Amsterdam
Author-Name: Casper G. de Vries
Author-Email: cdevries@few.eur.nl
Author-Workplace-Name: Erasmus University Rotterdam
Title: A Hybrid Joint Moment Ratio Test for Financial Time Series
Abstract: We advocate the use of absolute moment ratio statistics in conjunctionwith standard variance ratio statistics in order to disentangle lineardependence, non-linear dependence, and leptokurtosis in financial timeseries. Both statistics are computed for multiple return horizonssimultaneously, and the results are presented in a comprehensive wayusing a graphical device. We construct a formal joint testing procedurebased on bootstrapped and block-bootstrapped uniform confidenceintervals. The methodology is hybrid because it combines a formaltesting procedure with volatility curve pattern recognition based onexpert opinions. An application to forex data illustrates theprocedure.
File-Url: https://papers.tinbergen.nl/98104.pdf
File-Format: application/pdf
File-Size: 1174205 bytes
Handle: RePEc:tin:wpaper:19980104