A Markov-Switching Vector Error Correction Model of the Indian Stock Prices and Trading Volume

Abstract

Using weekly data from the Indian stock markets, the relationship between stock price and trading volume at an aggregated market level are examined using a Markov Switching-Vector Error Correction Model (MS-VECM), where deviations from the long run equilibrium are characterized by different rates of adjustment depending on the state of a hidden Markov chain. The long run dynamics are characterized by one co integrating vector relating the price to trading volume. We find stock price is weakly exogenous. The MS-VECM with two regimes provides a good characterization of the Indian stock market and performs well relative to other linear and nonlinear models. The two regimes are well identified as the first regime of high volatility and the second regime of modest volatility. The regime with high volatility is found to be associated with important local and international events (social, economic, & political) affecting the Indian Stock market.

Keywords: Indian Equity Market,Trading volume, Cointegration, Markov Switching

JEL Classification: C32, G10