Abstract
This study examines the existence of nonlinear serial dependence in five stock markets in the Middle East and Africa. The results from the application of a battery of nonlinearity tests reveal that after removing all short-term linear dependence, the stock returns still contain predictable nonlinearities that contradict the unpredictable criterion of weak-form efficient markets hypothesis.
Acknowledgement
The author would like to thank Universiti Malaysia Sabah for giving him a scholarship to pursue his PhD study in Monash University.
Notes
1 Patterson and Ashley (Citation2000) and Kyrtsou and Serletis (Citation2006) provided a review of those nonlinearity tests that are widely employed in the literature.
2 The toolkit can be downloaded from Richard Ashley's webpage at http://ashleymac.econ.vt.edu/ashleyhome.html, while instructions and interpretations of all the tests are given in chapter 3 of Patterson and Ashley (Citation2000).
3 The references and descriptions of these tests are deliberately omitted due to space constraint. The reader is to refer to the detailed discussion in Patterson and Ashley (Citation2000).
4 Another limitation of conventional efficiency tests as criticized by Saadi et al. (Citation2006) is that the detected autocorrelation could possibly due to non-synchronous trading, which is not genuine predictability but rather a statistical illusion. The above pre-whitening procedure not only obviates the need to adjust the returns series from the confounding effect of non-synchronous trading, but also addresses the interesting issue of whether stock returns are still predictable after removing linear dependence. See also Perron et al. (2002).