Risk prediction models with incomplete data with application to prediction of estrogen receptor-positive breast cancer: prospective data from the Nurses' Health Study

Table 1 Relative risk of estrogen receptor-positive breast cancer by quartile of postmenopausal plasma estradiol concentration (164 cases and 346 controls)^a

	Quartile of plasma estradiol
	1	2	3	4	P for trend
Relative risk	1	1.6	1.4	3.3
95% confidence interval		0.9–2.9	0.8–2.7	1.8–6.0	<0.001

^aUnconditional logistic regression controlling for matching factors (age, month and time of day of blood collection, and fasting status) and duration of premenopause, duration of menopause (separately for natural menopause and bilateral oophorectomy), birth index, age at first birth minus age at menarche, benign breast disease, duration of estrogen use, duration of estrogen and progestin use, duration of use of other types of postmenopausal hormones (PMH), current PMH use, past PMH use, average body mass index before and after menopause, and family history of breast cancer.

ISSN: 1465-542X