Timing the market: the economic value of price extremes

Financial Innovation

Table 18 Granger Causality Tests on PMG and PML: Decomposition with High Price Extremes

	Panel A: Monthly Data Observations			Panel B: Quarterly Data Observations
Lags	2	4	6	2	4	6
HS: PMG /→ PML	0.069	0.033	0.068	0.078	0.551	0.797
HS: PML /→ PMG	0.000	0.000	0.001	0.175	0.132	0.155
ST: PMG /→ PML	0.924	0.524	0.417	0.726	0.730	0.811
ST: PML ST /→ PMG	0.000	0.000	0.000	0.000	0.000	0.000
NK: PMG /→ PML	0.463	0.842	0.904	0.815	0.601	0.453
NK: PML /→ PMG	0.000	0.000	0.000	0.024	0.075	0.210
FT: PMG /→ PML	0.894	0.919	0.304	0.478	0.364	0.501
FT: PML /→ PMG	0.000	0.000	0.000	0.006	0.031	0.028
NASDAQ:PMG /→ PML	0.001	0.004	0.055	0.614	0.022	0.124
NASDAQ:PML /→ PMG	0.000	0.000	0.000	0.000	0.000	0.000
SSEC: PMG /→ PML	0.056	0.016	0.006
SSEC: PML /→ PMG	0.032	0.080	0.310
TSEC: PMG /→ PML	0.719	0.655	0.218
TSEC: PML /→ PMG	0.000	0.000	0.000
KOSPI: PMG /→ PML	0.055	0.334	0.059
KOSPI: PML /→ PMG	0.000	0.000	0.000
DAX : PMG /→ PML	0.508	0.944	0.690
DAX: PML /→ PMG	0.000	0.000	0.000
CAC: PMG /→ PML	0.271	0.328	0.269
CAC: PML /→ PMG	0.000	0.000	0.000

Note: X /→Y means the null hypothesis that X does not Granger-causes Y. This table reports the p-values of the F -statistics. To make sure that there are enough data observations to perform Granger causality tests, therefore, for quarterly data observations, we only perform Granger causality tests on SP500, NASDAQ, FTSE100, HS, NK and ST.