Please use this identifier to cite or link to this item: https://doi.org/10.1016/S0378-4371(02)01886-1
Title: Statistical analysis of strait time index and a simple model for trend and trend reversal
Authors: Chen, K. 
Jayaprakash, C.
Keywords: Crossover
Hurst exponent
Non-Gaussian behavior
Random walk
Stock price
Strait Time Index
Issue Date: 1-Jun-2003
Citation: Chen, K., Jayaprakash, C. (2003-06-01). Statistical analysis of strait time index and a simple model for trend and trend reversal. Physica A: Statistical Mechanics and its Applications 324 (1-2) : 258-265. ScholarBank@NUS Repository. https://doi.org/10.1016/S0378-4371(02)01886-1
Abstract: We analyze the daily closing prices of the Strait Time Index (STI) as well as the individual stocks traded in Singapore's stock market from 1988 to 2001. We find that the Hurst exponent is approximately 0.6 for both the STI and individual stocks, while the normal correlation functions show the random walk exponent of 0.5. We also investigate the conditional average of the price change in an interval of length T given the price change in the previous interval. We find strong correlations for price changes larger than a threshold value proportional to √T; this indicates that there is no uniform crossover to Gaussian behavior. A simple model based on short-time trend and trend reversal is constructed. We show that the model exhibits statistical properties and market swings similar to those of the real market. © 2002 Elsevier Science B.V. All rights reserved.
Source Title: Physica A: Statistical Mechanics and its Applications
URI: http://scholarbank.nus.edu.sg/handle/10635/104911
ISSN: 03784371
DOI: 10.1016/S0378-4371(02)01886-1
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

1
checked on Jun 13, 2018

WEB OF SCIENCETM
Citations

1
checked on Jun 13, 2018

Page view(s)

53
checked on Jun 8, 2018

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.