Testing for efficiency and non-linearity in market and natural time series
Teo Jasic and
Journal of Applied Statistics, 2006, vol. 33, issue 2, 113-138
Time series in traded markets such as currencies and securities involve supply/demand interaction, so they might be expected to contain distinctive and identifiable structures in comparison with data based on natural phenomena such as river flows or sunspots. This paper tests this proposition using standard econometric tests including variance ratios, modified rescaled range (R/S) ratios and BDS statistics together with non-linear prediction models. Four time series of each type (market or natural) are subject to a battery of tests for random walk and non-linear dependence. Surprisingly, the tests provide no reliable discrimination between the two types of series or reveal any embedded specification differences.
Keywords: Efficiency tests; non-linearity; neural networks; market versus natural data (search for similar items in EconPapers)
References: View complete reference list from CitEc
Citations: View citations in EconPapers (3) Track citations by RSS feed
Downloads: (external link)
Access to full text is restricted to subscribers.
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
Persistent link: https://EconPapers.repec.org/RePEc:taf:japsta:v:33:y:2006:i:2:p:113-138
Ordering information: This journal article can be ordered from
Access Statistics for this article
Journal of Applied Statistics is currently edited by Robert Aykroyd
More articles in Journal of Applied Statistics from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().