What active labour market programmes work for immigrants in Europe? A meta-analysis of the evaluation literature

Table 5 Sensitivity analysis

	Preferred	Variation
ALMP type (baseline: training)
Wage subsidy	1.1301**	1.2955**
	(0.5116)	(0.6004)
Public works	−0.2983	−0.2629
	(0.4579)	(0.4553)
Services/sanctions	0.2386	0.2203
	(0.4049)	(0.4010)
Other programmes	−0.9004**	−1.0741**
	(0.3530)	(0.4343)
Method	yes	yes
Programme characteristics	yes	yes
Sample characteristics	yes	yes
Contextual controls	UE	UE
Number of observations	93	86
Pseudo R-squared	0.1777	0.1821
Akaike information criterion	180.4334	171.6131

The table displays the estimated coefficients of ordererd probit models. Heteroskedasticity-robust standard errors are in parentheses. "Preferred" reproduces the results from column (5) in Table 4. “Variation” tightens the definition of ALMP and the short run, eliminating 6 studies. UE is for unemployment rate. ** denotes p < 0.05.