A critical appraisal of epidemiological studies comes from basic knowledge: a reader's guide to assess potential for biases

Table 2 Example of confounding in a hypothetical cohort study of intrauterine device use and salpingitis [8]

			Salpingitis
			Yes	No	Total	Proportion with salpingintis
All women (n = 2,000)	Use of IUD	Yes	45	955	1,000	4·5 %
		No	15	985	1,000	1·5 %
		$Crude RR = \frac{4.5 %}{1.5 %} = 3.0 (95 % CI 1.7 - 5.4)$
			Salpingitis
			Yes	No	Total	Proportion with salpingintis
Women with 1 sexual partner (n = 1,200)	Use of IUD	Yes	3	297	300	1·0%
		No	9	891	900	1·0%
		$RR = \frac{1.0 %}{1.0 %} = 1.0$ (95% CI 0.27-3.67)
			Salpingitis
			Yes	No	Total	Proportion with salpingintis
Women with >1 sexual partner (n = 800)	Use of IUD	Yes	42	658	700	6·0 %
		No	6	94	100	6·0 %
		$RR = \frac{6.0 %}{6.0 %} = 1.0$ (95% CI 0.43-2.29)

ISSN: 1749-7922