Hypertension: Development of a prediction model to adjust self-reported hypertension prevalence at the community level

Table 5 Sensitivity, specificity and agreement indicators for each determinant investigated (sex, educational level, income level) (NHANES Urban Sample N = 1114)

	Sensitivity	Specificity	Accuracy	Kappa
	P(CH = 1\|SR = 1)	P(CH = 0\|SR = 0)	Overall agreement)
Full sample	0.92	0.86	0.88	0.77
Age
25-34	0.93	0.87	0.89	0.78
35-49	0.99	0.70	0.83	0.67
50+	0.99	0.68	0.84	0.60
Gender
Females	0.94	0.89	0.90	0.75
Males
Marital Status
Current Married	0.91	0.86	0.88	0.76
Not Married	0.91	0.84	0.86	0.77
Race/ethnicity
Latino	0.99	0.88	0.90	0.77
Non-Hispanic White	0.92	0.86	0.87	0.74
Non-Hispanic Black	0.93	0.84	0.87	0.76
Education
<12	0.96	0.83	0.88	0.75
12	0.93	0.85	0.87	0.76
12+	0.90	0.88	0.88	0.76
Annual Household Income
<$10,000	0.96	0.82	0.87	0.76
$10,000-19,999	0.93	0.89	0.90	0.76
$20,000-34,999	0.89	0.85	0.86	0.77
$35,000+	0.90	0.89	0.90	0.77

Accuracy is the proportion of true results (both true positive and true negative). Refer to Additional file 1.

ISSN: 1472-6963