Skip to main content

Table 2 Poisson models measuring primary outcomes over the 6-month post-randomization period

From: Optimizing responsiveness to feedback about antibiotic prescribing in primary care: protocol for two interrelated randomized implementation trials with embedded process evaluations

Dependent variable Offset (denominator) Adjustment Additional details
Number of antibiotics Log of patient visits in those aged 65 or greater Log of the baseline prescription rate (1 year pre-intervention) as well as physician years since medical school and sex [23] Robust standard errors will be used, accounting for the correlation of multiple physicians at the same office-location using an exchangeable correlation.
Number of unnecessary antibiotics Log of patient visits for presumed viral condition
Number of broad-spectrum antibiotics Log of total antibiotic prescriptions
Number of prolonged antibiotics Log of total antibiotic prescriptions