Fig. 4From: Challenges of using external data in clinical trials- an illustration in patients with COVID-19Estimation of 28-day mortality rate using power prior models according to the power model parameter, \(a_0\). The blue lines indicate the position of the standard Bayes estimate from only the Covidicus trial data (when \(a_0=0\)) and that of ignoring heterogeneity in trial data (when \(a_0=1\))Back to article page