An empirical data analysis of "price runs" in daily financial indices: dynamically assessing market geometric distributional behavior

Olivares-Sanchez, Hector Raul, Rodriguez-Martinez, Carlos Manuel, Coronel-Brizio, Hector Francisco, Scalas, Enrico, Seligman, Thomas Henry and Hernandez-Montoya, Alejandro Raul (2022) An empirical data analysis of "price runs" in daily financial indices: dynamically assessing market geometric distributional behavior. PLoS One, 17 (7). e0270492. ISSN 1932-6203

[img] PDF - Accepted Version
Restricted to SRO admin only
Available under License Creative Commons Attribution.

Download (342kB)
[img] PDF - Published Version
Available under License Creative Commons Attribution.

Download (3MB)

Abstract

In financial time series there are time periods in which market indices values or assets prices increase or decrease monotonically. We call those events "price runs", "elementary uninterrupted trends" or just "uninterrupted trends". In this paper we study the distribution of the duration of uninterrupted trends for the daily indices DJIA, NASDAQ, IPC and Nikkei 225 during the period of time from 10/30/1978 to 08/07/2020 and we compare the simple geometric statistical model with p = 1/2 consistent with the EMH to the empirical data. By a fitting procedure, it is found that the geometric distribution with parameter p = 1/2 provides a good model for uninterrupted trends of short and medium duration for the more mature markets; however, longest duration events still need to be statistically characterized. Estimated values of the parameter p were also obtained and confirmed by calculating the mean value of p fluctuations from empirical data.
Additionally, the observed trend duration distributions for the different studied markets are compared over time by means of the Anderson-Darling (AD) test, to the expected
geometric distribution with parameter p = 1/2 and to a geometric distribution with a free parameter p, making possible to assess and compare different market geometric behavior for different dates as well as to measure the fraction of time runs duration from studied markets are consistent with the geometric distribution with p = 1/2 and in parametric free way.

Item Type: Article
Schools and Departments: School of Mathematical and Physical Sciences > Mathematics
Research Centres and Groups: Probability and Statistics Research Group
SWORD Depositor: Mx Elements Account
Depositing User: Mx Elements Account
Date Deposited: 27 Jun 2022 08:32
Last Modified: 08 Jul 2022 16:30
URI: http://sro.sussex.ac.uk/id/eprint/106623

View download statistics for this item

📧 Request an update