Forecast Kulim (M) Berhad share prices using Markov chain with and without missing values

Lai, Yee Shan (2008) Forecast Kulim (M) Berhad share prices using Markov chain with and without missing values. Universiti Malaysia Sabah. (Unpublished)

[img]
Preview
Text
ae0000002048.pdf

Download (1MB) | Preview

Abstract

Stocks are a part of nearly any investment portfolio. Hence, it is wise for us to study about stock market and might as well understand the changes in prices. The data series consist of daily share closing prices of Kulim (M) Berhad from January 2000 to December 2006. Remaining daily closing prices for the year 2007 are kept for post sample accuracy checking. The objective of this study is to apply Markov chain as a forecasting tool. Another objective of this study is to determine the significance of with and without estimating the missing values. Missing values are estimated using least-squares regression analysis, which consists of three methods of curve-fitting specifically the Linear curve, Quadratic curve, and Cubic curve. Each set of data with and without estimating missing values is analysed by using 5-States, 7 -States, 9-States, and 11-States Markov chain method. Results show that there are no significant differences in estimating the missing values. Here in this study, Markov chain is not a successful forecasting tool. Forecasted results have not correctly predicted the future trend of KULIM share prices within the sample period of study.

Item Type: Academic Exercise
Keyword: Markov chain, stock market, investment, closing price, forecasting tool
Subjects: Q Science > QA Mathematics
Department: SCHOOL > School of Science and Technology
Depositing User: SITI AZIZAH BINTI IDRIS -
Date Deposited: 24 Mar 2014 14:03
Last Modified: 13 Oct 2017 09:33
URI: https://eprints.ums.edu.my/id/eprint/8565

Actions (login required)

View Item View Item