Time Series Analysis Using ARCH Models: A Case Analysis of Australian Stock Index

Abstract

Australian All Ordinaries Stock Index has been in the headline since 1997 for its tear jerking effect on the stock exchange. Present work attempts to develop a realistic time-series model to explain the behavior of the stock price data during 2 January 1997 to 29 December 2006 collected from www.yahoofinance.com. To begin with residual analysis reveals that assumption of constant one period ahead forecast variance does not hold true. Accordingly, a new class of stochastic processes, called Autoregressive Conditional Heteroscedastic (ARCH) is studied. To this end, Computer programs on Ms-Excel have been used to fit the ARCH model.