Effects of Markov Chain in Finite State: Regime-Dependent Volatility Analysis Using Snedecor’s F-Distribution
Abstract
In this paper stochastic matrix of closing stock price data were transformed into 3-steps transition probability matrix. The probabilities of future stock price movements were known. The iterations of weekly predictions of price changes were considered on different days which after one iteration converged. More so theorems of steady-state were applied on the stochastic matrix results of stock price movements. The theorems were proved to show stochastic formation of memory- less property. From the solution matrix of stochastic analysis showed that, different price movement prediction in the near future. Also, an F-test based on Snedecor’s F-distribution was applied to three price series N1, N2, N3 to compare volatility. Tests were conducted on raw prices and on log-returns to approximate financial return behavior. N2 had zero variance in both levels and returns, indicating a non-stochastic series. For N1 versus N3, the F-statistics were 2.26 on raw prices and 2.52 on log-returns with 1 2 1 1 2. df df or or = = = Both were far below the 5% critical values, showing no statistically significant difference in variance. Structural break testing on N1 was not feasible due to insufficient observations; which is a tool for proper decision making in the day-to-day activities of stocks are hopeful for future investment plans both short or long term respectively.
Keywords
References
More Articles from INTERNATIONAL JOURNAL OF APPLIED SCIENCES AND MATHEMATICAL THEORY
Author: Samson Yunusa, Imande Terdon Terlumun,, Etuk Emmanuel Dan, and Micah Michael
Author: Ejes, Valentine, Liberty Ebiwareme
Author: Uwakwe, J. I., Anyanwu, E., Inalegwu, N.
Author: Xi Yang, Wenzhuo Zhang
Author: Olamiji Onafowokan1, Olawale Fadugba2, Deborah Okunola1, Alex Mendy1
