The social and economic determinants of suicide in Canadian provinces

Health Economics Review

Table 6 Difference GMM estimates

	Suicide	Suicide (M)	Suicide (F)	Suicide rate	Suicide rate (M)	Suicide rate (F)
Gini Index	−2.004	−0.208	−11.727**	−0.884	−1.015	0.131
GDP per Capita	2.371***	1.704**	6.463***	0.183	0.186	−0.003
GDP growth	−2.597***	−3.043***	−1.407	−0.188*	−0.228*	0.040
Unemployment rate	0.079***	0.015	0.423***	0.012	0.005	0.007**
Female labor participation	0.005	0.012	−0.033	−0.003	−0.002	−0.001
Divorce rate	0.001	0.013	−0.039	0.002	0.006	−0.004***
Alcohol sales	−1.402***	−1.882*	−0.068	−0.270*	−0.288*	0.018
Low income	0.798***	0.869**	0.977***	0.154**	0.137**	0.017
Immigration rate	0.003***	0.002	0.013***	0.001	−0.000	0.001***
Dependency ratio	11.147	15.159	1.551	4.169	2.128	2.042
Observations	40	40	40	40	40	40
Hansen (p-value)	1.000	1.000	1.000	1.000	1.000	1.000
AR(1)	0.136	0.164	0.110	0.051	0.115	0.121
AR(2)	0.144	0.161	0.257	0.097	0.056	0.296

Note: The dependent variable is the log of suicide and the suicide rate, for total population, male and female subsamples. Estimation is robust difference-GMM. Lagged regressors are used as suitable instruments. Robust heteroskedastic-consistent standard errors are used in all inference. The Hansen test evaluates the validity of the instrument set, i.e., tests for over-identifying restrictions. AR(1) and AR(2) are the Arellano-Bond autocorrelation tests of first and second order (the null is no autocorrelation), respectively. A constant term has been estimated but it is not reported for reasons of parsimony. *, **, *** denote significance at 10, 5 and 1% levels.

ISSN: 2191-1991