Table 3. Nowcasting summary (in-sample).

The whole analyzed period 01/2004-12/2013 is covered here. Model in Eq 2 is used here with varying maximum lag L. Joint significance of variables is a simple F-test based on heteroskedasticity and autocorrelation consistent (HAC) standard errors (p-values are reported in the brackets). Adjusted coefficient of determination ${\bar{R}}^2$ controls for the number of independent variables used in the model.

		Czech Rep.	Hungary	Poland	Slovakia
Δu t−i significance	L = 3	48.115	0.965	0.290	11.424
		[< 0.01]	[> 0.10]	[> 0.10]	[< 0.01]
	L = 6	20.559	0.863	7.188	6.336
		[< 0.01]	[> 0.10]	[< 0.01]	[< 0.01]
	L = 12	10.361	2.120	8.332	1.871
		[< 0.01]	[< 0.05]	[< 0.01]	[< 0.10]
ΔlogGI t−i significance	L = 3	9.284	2.945	7.472	5.454
		[< 0.01]	[< 0.05]	[< 0.01]	[< 0.01]
	L = 6	5.944	3.815	5.929	3.638
		[< 0.01]	[< 0.01]	[< 0.01]	[< 0.01]
	L = 12	7.685	3.574	2.525	7.448
		[< 0.01]	[< 0.01]	[< 0.01]	[< 0.01]
${\bar{R}}^2$, without Google	L = 3	0.177	0.022	-0.009	0.044
	L = 6	0.288	-0.003	-0.016	0.044
	L = 12	0.280	0.249	0.467	0.161
${\bar{R}}^2$, with Google	L = 3	0.318	0.076	0.144	0.163
	L = 6	0.367	0.118	0.328	0.205
	L = 12	0.407	0.418	0.552	0.406