Table 4.

Regression weights from the Bayesian skew-normal multilevel models.

Parameter		GAD-7			PSS-10			PHQ-8
		Est	LI	UI	Est	LI	UI	Est	LI	UI
β	Intercept	− 0.02	− 0.44	0.37	− 0.01	− 0.47	0.42	− 0.03	− 0.42	0.37
	Gender	0.09	0.04	0.14	0.24	0.16	0.3	0.12	0.06	0.18
	Residence [1]	− 0.02	− 0.1	0.05	0.01	− 0.09	0.11	− 0.1	− 0.19	− 0.01
	Residence [2]	0.02	− 0.05	0.1	0.07	− 0.07	0.2	0.04	− 0.05	0.14
	Residence [3]	− 0.06	− 0.12	0.01	− 0.07	− 0.19	0.04	− 0.04	− 0.13	0.05
	Education	0.04	− 0.01	0.08	0.07	− 0.04	0.17	0.08	0.01	0.13
	GII	− 0.05	− 0.44	0.35	− 0.21	− 0.64	0.28	− 0.1	− 0.51	0.34
	Stringency	0.04	− 0.37	0.46	0.02	− 0.45	0.53	0	− 0.4	0.41
	S&P rating [L]	− 0.15	− 0.91	0.64	− 0.31	− 1.15	0.63	− 0.26	− 1.01	0.58
	S&P rating [Q]	0.07	− 0.64	0.7	− 0.22	− 0.94	0.56	0.04	− 0.6	0.72
σ	Residual SD	0.93	0.9	0.96	0.94	0.92	0.97	0.96	0.93	0.99
α	Skewness	7.84	6.2	9.89	− 1.02	− 1.37	− 0.44	5.37	4.4	6.47
R2	Pop. L. Eff	0.07	0.02	0.21	0.13	0.06	0.26	0.08	0.03	0.22

Est., posterior mean; LL and UL, lower and upper bounds of the 95% credibility interval; β, standardized regression weight.

Estimations in bold are credible. Variables were coded as follows- Gender: Men = 0, Women = 1; Residence: Village = 1, Town = 2, City = 3, Agglomeration = 4; Education: Bachelor = 0, Master or higher = 1; GII: high = 0, low = 1; Stringency: high = 0, low = 1; S&P rating: 0 = low risk, 1 = medium risk, 2 = high risk (speculative); L, rating linear; Q, quadratic trends.