Reemployment premium effect of furlough programs: evaluating Spain’s scheme during the COVID-19 crisis

Journal for Labour Market Research

Table 4 Propensity score matching quality checks

Sample	Pseudo R \(^{2}\)	LR \(\chi ^{2}\)	p \(> \chi ^{2}\)	Mean bias	Median bias
(I)	(II)	(III)	(IV)	(V)	(VI)
Unmatched_1q	0.282	1642.98	0.000	16.3	8.9
Matched_1q	0.016	141.75	0.000	4.0	3.6
Unmatched_2q	0.365	422.55	0.000	19.7	11.9
Matched_2q	0.078	77.02	0.001	8.4	8.0

Values of the pseudo R-squared coefficient and related tests on the joint hypothesis of non-significance of the control variables in (II), (III), and (IV). Mean and median bias in column (V) and (VI). Ideally, we would expect significant reductions in the bias measures and the pseudo R-squared after matching