Skip to main content
Fig. 1 | BMC Medical Research Methodology

Fig. 1

From: The necessity of validity diagnostics when drawing causal inferences from observational data: lessons from a multi-database evaluation of the risk of non-infectious uveitis among patients exposed to Remicade®

Fig. 1

Empirical equipoise, covariate balance, empirical calibration validity diagnostics and representativeness for IBD primary analysis

Key: Amb EMR = IQVIA Ambulatory Electronic Medical Records; ASMD = absolute standardized mean difference; CCAE = Merative™ MarketScan® Commercial Database; CI = Confidence Interval; Clinformatics® = Optum® De-Identified Clinformatics® Data Mart Database; EASE = expected absolute systematic error; HR = Hazard ratio; IBD = irritable bowel diseases (Crohn’s disease or ulcerative colitis); IBD comparator = golimumab, certolizumab pegol, ustekinumab, or vedolizumab; Optum® EHR = Optum® De-Identified Electronic Health Record; Pharmetrics = IQVIA Adjudicated Health Plan Claims Data; Remicade®(m) = Remicade® exposure; Target covariate prevalence = prevalence of baseline covariates in the initial Remicade® exposure cohort before study design restrictions were applied; Analytic covariate prevalence = prevalence of baseline covariates in Remicade® exposure cohort after study design restrictions were applied (i.e., PS matching)

Back to article page

BMC Medical Research Methodology

ISSN: 1471-2288

Contact us