Women’s employment, income and divorce in West Germany: a causal approach

Journal for Labour Market Research

Table 2 ATT-DiD employment effects in percentage points for main sample, group A and group B at t₀, t₃₆₅, t₇₃₀ and t₁₀₉₅

	Logit and kernel matching				GBM and odd weighting
	h bandwidth	Overall employment	Marginal employment	Regular employment	Overall employment	Marginal employment	Regular employment
Main sample
At day t₀	0.056	− 0.02	− 0.09***	0.08**	− 0.02	− 0.10***	0.09***
At day t₃₆₅	0.056	− 0.04	− 0.10***	0.06	− 0.03	− 0.10***	0.07*
At day t₇₃₀	0.056	− 0.01	− 0.09**	0.08*	− 0.01	− 0.09***	0.08**
At day t₁₀₉₅	0.056	0.01	− 0.07*	0.09**	0.00	− 0.08**	0.10**
Group A—women not regularly employed in t_-2189 to t₋₇₃₀
At day t₀	0.082	− 0.10	− 0.21***	0.13**	− 0.10*	− 0.22***	0.14***
At day t₃₆₅	0.082	− 0.08	− 0.25***	0.17***	− 0.06	− 0.24***	0.19***
At day t₇₃₀	0.082	− 0.02	− 0.23***	0.24***	− 0.01	− 0.23***	0.24***
At day t₁₀₉₅	0.082	0.00	− 0.22***	0.25***	0.00	− 0.22***	0.24***
Group B—women with strong labor market attachment (regular employment) in t₋₂₁₈₉ to t₋₇₃₀
At day t₀	0.038	− 0.03	− 0.04	0.00	0.00	− 0.04	0.03
At day t₃₆₅	0.038	− 0.06	− 0.04	− 0.03	− 0.04	− 0.03	− 0.01
At day t₇₃₀	0.038	− 0.04	− 0.04	− 0.03	− 0.02	− 0.02	− 0.01
At day t₁₀₉₅	0.038	− 0.04	− 0.01	− 0.04	− 0.01	− 0.02	− 0.01

Cumulative days of regular employment for group A in t₋₂₁₈₉ to t₋₇₃₀ equals zero and for group B is between 967 to 1460 days. Bandwidth h for kernel matching was chosen by leave-one-out cross-validation. Overall employment is marginal and/or regular employment. T₀ is the day the divorce file was opened. Difference-in-difference (DiD) estimation with respect to t₋₇₃₀ for all measure points. Matching (and odd weighting) was based on the propensity score. Propensity scores were estimated via a General Boosted Model (GBM) with higher order covariates and interaction terms (depth 3) as well as with a logit model based on covariates in linear form (see Table 5 in Appendix for all applied covariates)
*p < 0.05; **p < 0.01; ***p < 0.001