Unemployment in an Interdependent World

Table A4: Robustness Checks: Alternative construction of weighting matrix

	Normalization over all countries, by ∑i ωi						Normalization over all, by maxi ωi δ = 1.00, α_i = 1.00		Normalization over 20 OECD countries, by _i ωi δ = 1.00, α_i = 1.00
	δ= 0.75, αi = 1.00		δ= 1.50, αi = 1.00		δ = 1.00, α_i = 0.00		Normalization over all, by maxi ωi δ = 1.00, α_i = 1.00
	(1) IV	(2) OLS	(3) IV	(4) OLS	(5) IV	(6) OLS	(7) IV	(8) OLS	(9) IV	(10) OLS
u*	0.096^b		0.065^a		0.582^a		0.011^b		0.026^b
	(0.042)		(0.021)		(0.178)		(0.005)		(0.011)
b*		0.011^b		0.006^a		0.052^a		0.001^b		0.003^b
		(0.005)		(0.002)		(0.019)		(0.000)		(0.001)
b	0.098^a	0.085^a	0.098^a	0.087^a	0.098^a	0.089^a	0.101^a	0.088^a	0.100^a	0.087^a
	(0.019)	(0.020)	(0.019)	(0.019)	(0.018)	(0.019)	(0.019)	(0.019)	(0.019)	(0.020)
PMR	0.939^a	0.864^a		0.837^a	0.799^a	0.774^a	0.917^a	0.839^a	0.910^a	0.844^a
	(0.206)	(0.211)		(0.204)	(0.190)	(0.199)	(0.200)	(0.208)	(0.201)	(0.210)
Union density	-0.002	-0.003	-0.007	-0.006	0.001	-0.002	-0.007	-0.007	-0.005	-0.005
	(0.022)	(0.023)	(0.022)	(0.023)	(0.021)	(0.023)	(0.022)	(0.023)	(0.022)	(0.023)
High corporatism	-1.860^a	-1.635^a	-1.800^a	-1.608^a	-1.774^a	-1.594^a	-1.833^a	-1.619^a	-1.849^a	-1.638^a
	(0.394)	(0.420)	(0.395)	(0.421)	(0.381)	(0.411)	(0.392)	(0.419)	(0.393)	(0.419)
EPL	-0.271	-0.392	-0.349	-0.431	-0.283	-0.374	-0.282	-0.387	-0.257	-0.369
	(0.349)	(0.367)	(0.350)	(0.373)	(0.330)	(0.355)	(0.353)	(0.372)	(0.352)	(0.369)
gap	-0.608^a	-0.620^a	-0.614^a	-0.624^a	-0.610^a	-0.614^a	-0.611^a	-0.622^a	-0.611^a	-0.622^a
	(0.039)	(0.044)	(0.039)	(0.044)	(0.038)	(0.044)	(0.039)	(0.044)	(0.039)	(0.044)
* gap^*	0.028	-0.070	0.063	-0.004	0.924^a	0.596^b	0.015	0.004	0.007	0.000
	(0.096)	(0.097)	(0.045)	(0.045)	(0.298)	(0.269)	(0.011)	(0.011)	(0.008)	(0.008)
2nd stage statistics
RMSE	1.011	1.130	1.008	1.130	1.000	1.116	1.012	1.132	1.013	1.132
adj. R²	0.935	0.931	0.936	0.931	0.937	0.933	0.935	0.931	0.935	0.930
F		145.7		147.2		161.3		144.1		143.7
1st stage statistics (p-values)
partial R²	0.762		0.741		0.714		0.759		0.766
χ² -overidentification	0.667		0.843		0.0153		0.825		0.687
χ² -endogeneity	0.927		0.976		0.155		0.997		0.965

Robust standard errors in parentheses,^ap < 0.01,^bp < 0.05,^cp < 0.1. Number of observations: 397 in OLS and 374 in IV regressions. All regressions
contain a full set of country fixed-effects, year dummies, and an array of orthogonal shocks (TFP, terms of trade, real interest rate, and labor demand
shocks) as additional controls for business cycle comovements. Trade-weighted averages for foreign variables are denoted by asterisks. In IV regressions,
the foreign unemployment rate u* is instrumented by b*_-₁, PMR*_-₁ and gap*_-₁. The χ²-endogeneity test tests the null that u* is exogenous (and rejects
in all presented IV models). Overidentification is tested for using the Wooldridge robust Score test (invalidity of instruments or model misspecification
is rejected in all presented IV models).

CorPapers

Unemployment in an Interdependent World

More intriguing information