Observational Research on Alcohol Use and Chronic Disease Outcome: New Approaches to Counter Biases

Table 1

Comparison of alternative models for assessing the association between health status and alcohol consumption: offsetting residual confounding effects and applying intention-to-treat analysis (RR: relative risk).

	RR	95% confidence; interval		RR	95% confidence; interval		RR	95% confidence; interval		RR	95% confidence; interval
Alcohol use	Traditional model			Adjusted for residual confounding effects			Adjusted for intention-to-treat analysis			Adjusted for confounding and intention to treat
Lifetime abstainer	Reference			Reference			Reference			Reference
Former infrequent	1.14	1.08	1.21	1.03	0.97	1.09	*			*
Former regular	1.21	1.14	1.28	1.36	1.28	1.45	*			*
Current infrequent	0.99	0.93	1.05	0.98	0.92	1.05	1.06	1.00	1.12	1.04	0.99	1.10
Current light	0.77	0.72	0.82	0.87	0.82	0.93	0.92	0.87	0.97	0.99	0.93	1.04
Current moderate	0.66	0.61	0.72	0.78	0.71	0.84	0.85	0.79	0.92	0.93	0.86	1.00
Current heavier	0.83	0.75	0.91	1.03	0.93	1.13	0.96	0.88	1.05	1.08	0.99	1.17
Drinking status not reported	1.04	0.92	1.18	1.00	0.88	1.13	*			*

*: Intention-to-treat analysis applied.