Testing for Chaos and Nonlinearity in Taiwan Futures Returns

When Taiwan launched its stock index futures trading, the government frequently intervened in the stock market. In such a new anticipatory market with market intervention, the chaos theory predicts that feedbacks of traded price may result in nonlinearity and possibly, chaos. This paper uses the early historical data of Taiwan futures market to test the chaos theory of adaptive behavior. It is found that the variance ratio test indicates linear dependence in the raw returns. Then, tests based on the correlation dimension (CD), and the more powerful BDS statistic, confirm the presence of nonlinearity in the filtered time series. Then, the CD and the BDS statistic applied to the standardized residuals of the EGARCH model reject hetero skedasticity as the cause of nonlinearity. Finally, the test of the locally weighted regression (LWR), applied to the filtered time series, indicates the presence of chaos. These results show that government interventions can generate market adaptive behavior that will result in chaos. The findings may have relevant implications for risk management and market efficiency when investing in an anticipatory market with adaptive behavior.

並列關鍵字

BDS statistic ； Chaos ； EGARCH ； Futures market ； Nonlinearity

國際替代計量

全文下載

主題瀏覽