Statistical Inadequacy of GARCH Models for Asian Stock Markets

Abstract

This study employs the Hinich portmanteau bicorrelation test (Hinich 1996; Hinich and Patterson 1995) as a diagnostic tool to determine the adequacy of Generalised Autoregressive Conditional Heteroscedasticity (GARCH) models for eight Asian stock markets. The bicorrelation test results demonstrate that this type of model cannot provide an adequate characterisation for the underlying process of all the selected Asian stock markets. Further investigation using the windowed test procedure reveals that the violation of the covariance stationarity assumption as required by the GARCH process is due to the presence of transient epochs of dependencies in the data. The inadequacy of GARCH models has strong implications for the pricing of stock index options, portfolios selection, development of optimal hedging techniques and risk management.

Stock returns in emerging markets and the use of GARCH models

“…These results are similar to the previous studies that analysed the inadequacy of using GARCH type of models in Asian countries (Lim et al, 2005) and European countries (Brooks and Hinich, 1998). Table 2 shows the number of nonsignificant windows using a sub-sample size of 200, 400 and 800 observations at the 10%, 5% and 1% significance level.…”

“…Brooks and Hinich (1998) reported several European stock indices and found that GARCH model cannot be considered a full representation of the process generating financial market returns. Lim et al (2005) employed the Hinich portmanteau bicorrelation test to determine the adequacy of the GARCH model for eight Asian stock markets and found that this model cannot provide an adequate characterization for the underlying process of these Asian stock market indices.…”

Nonlinearities and Garch Inadequacy for Modeling Stock Market Returns: Empirical Evidence From Latin America

“…This result provides evidence of the inadequacy of using GARCH models for Latin American stock market indices. These results are similar to those from previous studies that analyzed the inadequacy of using GARCH type of models in Asian countries [Lim et al (2005)] and European countries [Brooks and Hinich (1998)]. Table 2 shows the number of nonsignificant windows using subsample size of 200, 400, and 800 observations at 10%, 5%, and 1% significance level.…”

“…Our results present a smaller number of significant windows than the Asian stock markets studied by Lim et al (2005), where the GARCH assumption was analyzed with a methodology similar to ours. However, the percentage of significant windows is still high.…”

Are daily and weekly load and spot price dynamics in Australia's National Electricity Market governed by episodic nonlinearity?

“…This implies that the tails of the empirical distribution functions of the spot prices returns in particular taper down to zero much more gradually than would the tails of the normal distribution (Lim, Hinich, Liew (2005, p.270)). Not unexpectedly, the Jarques-Bera (JB) Normality Test for all of the returns series listed in both tables indicates that the null hypothesis of normality is strongly rejected at the conventional 1% level of significance.…”