Table 6. Results from unit root test...

Table 6.

Results from unit root test with smooth breaks

	Level shift					Level and trend shift
Country	ADF(k^*)	p	k*	Ftrig	p-val.	ADF(k^*)	p	k^*	Ftrig	p-val.
Greece	−3.596^*	12	1	7.329^***	0.000	−3.610	12	1	4.826^***	0.008
Ireland	−3.392^**	3	3	3.165^**	0.042	−3.646^*	3	3	3.644^**	0.026
Italy	−2.403	11	2	2.311	0.100	−3.247	11	2	3.714^**	0.024
Portugal	−3.591^*	10	1	5.443^***	0.004	−3.525	10	1	4.431^**	0.012
Spain	−2.809	9	2	0.800	0.449	−3.524^*	9	3	3.391^*	0.092

	Level shift					Level and trend shift
Country	ADF(k^*)	p	k*	Ftrig	p-val.	ADF(k^*)	p	k^*	Ftrig	p-val.
Greece	−3.596^*	12	1	7.329^***	0.000	−3.610	12	1	4.826^***	0.008
Ireland	−3.392^**	3	3	3.165^**	0.042	−3.646^*	3	3	3.644^**	0.026
Italy	−2.403	11	2	2.311	0.100	−3.247	11	2	3.714^**	0.024
Portugal	−3.591^*	10	1	5.443^***	0.004	−3.525	10	1	4.431^**	0.012
Spain	−2.809	9	2	0.800	0.449	−3.524^*	9	3	3.391^*	0.092

Notes:

The optimal lag(s), p, were determined by the t-stat significance of the last lagged dependent variable at the 10% significance level by setting the maximum number of lags to 12. The optimal Fourier frequency k^* was selected by minimizing the sum of squared residuals from OLS estimation with k ∈ [1,…,5]. Ftrig is the usual F-statistic for testing the null hypothesis of the absence of trigonometric terms (i.e. δ₁=δ₂ = 0) in equation (8) for the model with level shift and equation (9) for the model with level and trend shift by using k = k^*. The critical values for Fourier ADF, ADF(k^*), test are available in Enders and Lee (2012).

***

(1%),

(5%) and

(10%)

[ViewLarge]