Prevalence estimation by joint use of big data and health survey: a demonstration study using electronic health records in New York city

Table 1 Simulation studies: prevalence estimate by four methods

True Population Prevalence		Prevalence Estimate (95% CI)
Prevalence (p₁) based on outcome in health survey (Y₁)	Prevalence (p₂) based on outcome in EHR (Y₂)	Health Survey (n₁ = 500)	Post-stratified EHR	Mosteller estimator	Subject-level imputation estimator
0.3	0.30	0.300	0.299	0.300	0.303
0.3	0.31	0.300	0.309	0.303	0.302
0.3	0.32	0.299	0.319	0.305	0.302
0.3	0.33	0.298	0.329	0.305	0.303
0.3	0.35	0.300	0.349	0.308	0.304

The size of health survey (n₁) and the size of subjects linked between two sources (n₁₂) are both 500

ISSN: 1471-2288