LINEAR VECTOR ERROR CORRECTION MODEL VERSUS MARKOV SWITCHING VECTOR ERROR CORRECTION MODEL TO INVESTIGATE STOCK MARKET BEHAVIOUR

Seuk-Wai Phoong1*, Mohd Tahir Ismail2 and Siok-Kun Sek3

1,2,3 School of Mathematical Sciences,
Universiti Sains Malaysia, 11800, Pulau Pinang, Malaysia

*Corresponding author: wai_phoong@yahoo.com

 

ABSTRACT

The stock market can reflect the economy of a country. The movement of the stock market index may imply the economic condition in general. The 1997 Asian Financial Crisis and the 2008 Global Economic Crisis are examples of share depressions that impacted countries’ inflation, unemployment rates and gross national product (GNP). This study investigates how oil and gold prices impact the stock exchange using a linear vector error correction model (VECM) and a Markov switching vector error correction model (MS-VECM). The results show that oil and gold prices affect the stock market returns for the four selected countries, namely Malaysia, Singapore, Thailand and Indonesia. The MS-VECM is able to capture every change in the transition probabilities of the financial time series data and is more reliable than the linear VECM for examining the effect of oil and gold prices on the stock market.

Keywords: vector error correction model, Markov switching model, stock market, oil price, gold price

Full text        EPUB