Table A1 Chow–denning joint variance...

Table A1

Chow–denning joint variance ratio test results based on five-day returns

Market	Dof	Homoscedasticity robust test statistics max \|z\|		Heteroscedasticity robust test statistics max \|z\|
Market	Dof	Panel A	Panel B	Panel A	Panel B
Australia	755	14.08	14.08	4.98	4.98
Canada	751	14.03	14.03	5.34	5.34
France	767	14.17	14.17	7.76	7.76
Germany	761	15.16	15.16	8.28	8.28
Hong Kong	738	13.77	13.77	8.37	8.37
Israel	720	13.16	13.16	7.11	7.11
Japan	734	14.97	14.97	5.34	5.34
Sweden	752	15.19	15.19	5.50	5.50
UK	756	14.23	14.23	8.39	8.39
US	753	16.90	16.90	5.44	5.44
Brazil	740	16.12	16.12	7.08	7.08
Chile	746	14.52	14.52	6.77	6.77
China	727	13.57	13.57	10.18	10.18
Greece	741	14.16	14.16	7.31	7.31
India	740	15.37	15.37	8.72	8.72
Malaysia	736	14.01	14.01	6.77	6.77
Mexico	750	15.77	15.77	6.18	6.18
Poland	745	14.30	14.30	7.22	7.22
Russia	743	14.60	14.60	6.85	6.85
South Africa	746	13.37	13.37	7.72	7.72

Market	Dof	Homoscedasticity robust test statistics max \|z\|		Heteroscedasticity robust test statistics max \|z\|
Market	Dof	Panel A	Panel B	Panel A	Panel B
Australia	755	14.08	14.08	4.98	4.98
Canada	751	14.03	14.03	5.34	5.34
France	767	14.17	14.17	7.76	7.76
Germany	761	15.16	15.16	8.28	8.28
Hong Kong	738	13.77	13.77	8.37	8.37
Israel	720	13.16	13.16	7.11	7.11
Japan	734	14.97	14.97	5.34	5.34
Sweden	752	15.19	15.19	5.50	5.50
UK	756	14.23	14.23	8.39	8.39
US	753	16.90	16.90	5.44	5.44
Brazil	740	16.12	16.12	7.08	7.08
Chile	746	14.52	14.52	6.77	6.77
China	727	13.57	13.57	10.18	10.18
Greece	741	14.16	14.16	7.31	7.31
India	740	15.37	15.37	8.72	8.72
Malaysia	736	14.01	14.01	6.77	6.77
Mexico	750	15.77	15.77	6.18	6.18
Poland	745	14.30	14.30	7.22	7.22
Russia	743	14.60	14.60	6.85	6.85
South Africa	746	13.37	13.37	7.72	7.72

Note(s): 1. This table presents five-day return results of Chow–Denning tests (test of martingale hypothesis). The presented are Max |z| with probability approximation using studentized maximum modulus with parameter value 4 and infinite degrees of freedom

2. All the test statistics are statistically significant (different from 1), using a critical value of 2.49 (panel A) and using the confidence intervals calculated with the Wild Bootstrapping method (panel B)

3. The results strongly reject the null hypothesis of a martingale across all markets

4. We also ran the above tests in panel settings under the assumption that cross-sections are independent, with cross-section heterogeneity of the processes. The combined the p-values from cross-section results using the Fisher approach as in Maddala and Wu (1999) were all highly significant for both developed and emerging market panels

[ViewLarge]

Sharing Unavailable