TABLE 2—

Results From Longitudinal Analysis on the Proportion of Firearm Suicides in 13 Countries

	Model A: Unconditional Means Model		Model B: Unconditional Growth Model		Model C: Composite Model
	Estimate (SE)	P	Estimate (SE)	P	Estimate (SE)	P
Fixed effects
Initial status interception)	–1.82 (.30)	> .001	–1.63 (.30)	> .001	.431 (.316)	.19
Rate of change (time 0, 1, 2)			–.198 (.07)	.017	–.070 (.048)	.24
Suicide rate					–.033 (.015)	.052
Proportions of households owning firearms					1.03 (.087)	> .001
Variance components
Within country	.118 (.033)	> .001	.026 (.010)	.011	.029 (.012)	.03
In initial status	1.15 (.465)	.014	1.14 (.457)	.012	.089 (.050)	.08
In rate of change			.053 (.026)	.04	.014 (.015)	.34
Covariance			–.010 (.077)	.89	.031 (.031)	.32
Goodness-of-fit
Deviance	71.7		53.0		12.1
Akaike’s information criterion	–37.8		–30.5		–10.0
Bayesian information criterion	–39.5		–33.8		–13.1