Figure 2

Probability of correctly identifying the optimal dose for Scenario 1 for the Braun, Gumbel and Independence model for various combinations of the true model, level of correlation and prior specification for the regression parameters in the logistic regression models for efficacy and toxicity. PS 1: β _0,T ∼N(−3,3), β _0,E ∼N(−1,3), ${\beta }_{1,T}\sim \mathit{\text{Gamma}}\left(\frac{1}{4},\frac{1}{4}\right)$, ${\beta }_{1,E}\sim \mathit{\text{Gamma}}\left(\frac{1}{4},\frac{1}{4}\right)$; PS 2: β _0,T ∼N(−3,5), β _0,E ∼N(−1,5), ${\beta }_{1,T}\sim \mathit{\text{Gamma}}\left(\frac{1}{4},\frac{1}{4}\right)$, ${\beta }_{1,E}\sim \mathit{\text{Gamma}}\left(\frac{1}{4},\frac{1}{4}\right)$; PS 3: β _0,T ∼N(−3,3), β _0,E ∼N(−1,3), ${\beta }_{1,T}\sim \mathit{\text{Gamma}}\left(\frac{1}{25},\frac{1}{25}\right)$, ${\beta }_{1,E}\sim \mathit{\text{Gamma}}\left(\frac{1}{25},\frac{1}{25}\right)$; PS 4: β _0,T ∼N(−3,5), β _0,E ∼N(−1,5), ${\beta }_{1,T}\sim \mathit{\text{Gamma}}\left(\frac{1}{25},\frac{1}{25}\right)$, ${\beta }_{1,E}\sim \mathit{\text{Gamma}}\left(\frac{1}{25},\frac{1}{25}\right)$.