Table 3.

Wald Tests for Assesing the Relative Importance of Winter Volatility

	(1)	(2)	(3)	(4)	(5)	(6)
	χ2(1) Statistic from Wald Tests of the Null Hypotheses that the Effects of Winter Volatility are not Different from the Effects of:
	Spring Volatility		Summer Volatility		Autumn Volatility
	Baseline Model	Full Model	Baseline Model	Full Model	Baseline Model	Full Model
Test on the First-Order Effect	2.490 [0.115]	0.438 [0.508]	1.075 [0.300]	1.846 [0.174]	3.844** [0.050]	0.774 [0.379]
Test on the Second-Order Effect	6.426** [0.011]	5.034** [0.025]	2.087 [0.149]	5.082** [0.024]	4.215** [0.040]	2.033 [0.154]

Notes:

⁽ⁱ⁾Odd-numbered columns of this table compare the relevant coefficient estimates from the specification presented in Column 7 of Table 2 with corresponding ones presented in Columns 1, 3, and 5, respectively, of that table;

⁽ⁱⁱ⁾Even-numbered columns of this table compare the relevant coefficient estimates from the specification presented in Column 8 of Table 2 with corresponding ones presented in Columns 2, 4, and 6, respectively, of that table;

⁽ⁱⁱⁱ⁾p-values of the χ²(1) statistics are reported in square brackets;

^(iv)*** denotes statistical significance at the 1% level, ** at the 5% level, and * at the 10% level.