. 2020 Jan 2;7(1):e14035. doi: 10.2196/14035

Table 3.

Main effects of ordinary least squares regression models with robust standard errors predicting excessive alcohol use (Alcohol Use Disorders Identification Test-Consumption) in 3 countries.

Model		United States				South Korea				Finland
Model		B^a	SE	Beta	P value	B	SE	Beta	P value	B	SE	Beta	P value
Model 1
	Constant	–4.9^b	0.50^b	—^c	<.001^b	–5.1^b	0.69^b	—	<.001^b	–.51	0.67	—	.44
	Perceived loneliness	.18^b	0.04^b	.12^b	<.001^b	.13^b	0.06^b	.06^b	.02^b	0.01	0.05	0.01	.82
	Age (years)	.35^b	0.02^b	.41^b	<.001^b	.42^b	0.03^b	.38^b	<.001^b	.24^b	0.03^b	.23^b	<.001^b
	Gender^d	–.53^b	0.14^b	–.10^b	<.001^b	–.28	0.18	–.04	.13	–.37^b	0.17^b	–.06^b	.034^b
	Living alone^e	0.27	0.24	0.03	.27	1.1^b	0.31^b	.10^b	.001^b	0.28	0.19	0.04	.15
	R²	0.21	—	—	—	0.18	—	—	—	0.06	—	—	—
Model 2
	Constant	–5.5	0.58	—	>.001	–7.1^b	0.90^b	—	<.001^b	–1.9	0.83	—	.02
	Perceived loneliness	0.07	0.04	0.05	.13	.22^b	0.06^b	.11^b	.001^b	–.02	0.06	–.01	.68
	Age (years)	.33^b	0.02^b	.40^b	<.001^b	.42^b	0.03^b	.39^b	<.001^b	.22^b	0.03^b	.21^b	<.001^b
	Gender^d	–.56^b	0.14^b	–.10^b	<.001^b	–.33	0.19	–.05	.07	–.70^b	0.17^b	–.12^b	<.001^b
	Living alone^e	0.26	0.24	0.03	.27	.95^b	0.31^b	.09^b	.003^b	0.3	0.18	0.05	.11
	Belonging to friends	0.06	0.03	0.06	.06	.25^b	0.05^b	.16^b	<.001^b	.24^b	0.04^b	.20^b	<.001^b
	Belonging to an online community	0.02	0.03	0.02	.52	–.08	0.04	–.06	.05	–.12^b	0.03^b	–.10^b	.001^b
	Psychological distress	.08^b	0.01^b	.20^b	<.001^b	0.01	0.02	0.02	.59	.10^b	0.01^b	.21^b	<.001^b
	R²	0.24	—	—	—	0.2	—	—	—	0.12	—	—	—

^aUnstandardized regression coefficient.

^bStatistically significant results (P<.05).

^cValue not applicable.

^dGender reference category male.

^eLiving alone measured with a dummy variable (0=No, 1=Yes).