An Autoregressive Model with Suddenly Changing Parameters and an Application to Stock Market Prices

John S. Tyssedal and Dag Tjøstheim

Journal of the Royal Statistical Society Series C, 1988, vol. 37, issue 3, 353-369

Abstract: We consider autoregressive models where the coefficients are piecewise constant and change according to a Markov chain mechanism. Two methods of estimation are considered: the method of moments and the method of least squares. Moment estimates are shown to be consistent, but simulations show that their convergence could be very slow. Much better results are obtained by a two‐step least squares estimation algorithm. This algorithm is applied on a time series consisting of IBM closing stock prices, and the results are compared with other models that have been fitted to this series. The results are interpreted in the context of some models that are currently used for stock market data, and the major transition points are related to some specific economic events not noted by earlier investigators of the series.

Date: 1988
References: Add references at CitEc
Citations: View citations in EconPapers (13)

Downloads: (external link)
https://doi.org/10.2307/2347310

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:bla:jorssc:v:37:y:1988:i:3:p:353-369

Ordering information: This journal article can be ordered from
http://ordering.onli ... 1111/(ISSN)1467-9876

Access Statistics for this article

Journal of the Royal Statistical Society Series C is currently edited by R. Chandler and P. W. F. Smith

More articles in Journal of the Royal Statistical Society Series C from Royal Statistical Society Contact information at EDIRC.
Bibliographic data for series maintained by Wiley Content Delivery ().