Incidence rate ratios from Self-Controlled Case Series



A data frame with 46 rows and 4 variables:


Name of the drug


Whether the drug is a positive (1) or negative (0) control


The log of the incidence rate ratio


The standard error of the log of the incidence rate ratio


A dataset containing the incidence rate ratios (and standard errors) produced using a Self-Controlled Case Series (SCCS) design. The outcome is upper GI bleeding, the drug of interest (groundTruth = 1) is sertraline. Also included are 45 negative control drugs, for which we believe there to be no causal relation with upper GI bleeding. We used a database of medical records from general practices in the USA, the General Electric (GE) Centricity database, which contains data on 11.2 million subjects. We restricted on study period (start of 1990 through November 2003), age requirements (18 years or older), available time prior to event (180 days), and risk definition window (30 days following the prescription). Time 30 days prior to the first prescription was removed to account for possible contra-indications. Cases of upper GI bleeding were identified on the basis of the occurrence of ICD-9 diagnosis codes in the problem list. These codes pertain to esophageal, gastric, duodenal, peptic, and gastrojejunal ulceration, perforation, and hemorrhage, as well as gastritis and non-specific gastrointestinal hemorrhage. For more information on this set see Schuemie et al (2014).


Schuemie MJ, Ryan PB, Dumouchel W, Suchard MA, Madigan D. Interpreting observational studies: why empirical calibration is needed to correct p-values. Statistics in Medicine 33(2):209-18,2014