The unhappily unemployed return to work faster

Table 11 Dependent variable: duration in unemployment, measured in months

	(1)	(2)	(3)	(4)	(5)	(6)	(7)	(8)
	ols	ols	ols	ols	stcox	stcox	stcox	stcox
Age	0.487**	0.114	0.319	0.337	-0.0257***	-0.00759	-0.0296	-0.0314
	(0.209)	(0.317)	(0.221)	(0.221)	(0.00791)	(0.0116)	(0.0248)	(0.0248)
Age sq.	-0.00270	1.14e-06	-0.00340	-0.00359	0.000193*	4.38e-05	0.000331	0.000350
	(0.00263)	(0.00387)	(0.00263)	(0.00263)	(9.95e-05)	(0.000141)	(0.000296)	(0.000296)
Male	7.897***	6.016***	1.851***	1.951***	-0.309***	-0.267***	-0.228***	-0.238***
	(0.770)	(1.168)	(0.667)	(0.667)	(0.0287)	(0.0425)	(0.0758)	(0.0758)
Educ. Medium	-9.664***	-8.614***	-1.469*	-1.508*	0.333***	0.287***	0.154*	0.158*
	(0.890)	(1.244)	(0.783)	(0.782)	(0.0331)	(0.0451)	(0.0874)	(0.0873)
Educ. High	-13.43***	-11.14***	-2.288***	-2.327***	0.548***	0.481***	0.216**	0.226**
	(0.922)	(1.349)	(0.804)	(0.804)	(0.0344)	(0.0489)	(0.0905)	(0.0905)
Reg. Un	1.142***	1.080***	0.453***	0.456***	-0.0463***	-0.0458***	-0.0401***	-0.0405***
	(0.143)	(0.203)	(0.119)	(0.118)	(0.00538)	(0.00750)	(0.0136)	(0.0136)
Ben.Inc.	0.0110***	0.0153***	0.00566***	0.00565***	-0.000716***	-0.000479***	-0.000464**	-0.000465**
	(0.00109)	(0.00209)	(0.00153)	(0.00153)	(5.83e-05)	(7.93e-05)	(0.000191)	(0.000192)
Sp. Unmp		9.156***	1.396**	1.465**		-0.355***	-0.189**	-0.188**
		(1.166)	(0.708)	(0.708)		(0.0424)	(0.0810)	(0.0809)
Loss			-2.275***				0.225***
			(0.630)				(0.0717)
Δ H a p				0.298***				-0.0309***
				(0.0802)				(0.00898)
Reg. dummies	Yes	Yes	Yes	Yes	Yes	Yes	Yes	Yes
Constant	Yes	Yes	Yes	Yes
Observations	5725	3030	885	885	5501	2909	824	824
R-squared	0.122	0.146	0.092	0.093

Source: BHPS, waves 1–16, pooled data. Standard errors in parenthesis, *significant at 10%, **significant at 5%, ***significant at 1%. The reference category for education is low educational achievement.
Loss is a dummy = 1 when an individual reports a loss of happiness larger than 1 point when losing his job.
Δ Hap measures the initial change in happiness when becoming unemployed. Given that most observations of Diff-hap are negative, the results have to be interpreted as follows: if happier about losing a job, then one spends more time in unemployment.