Administrative Censoring in Ecological Analyses of Autism and a Bayesian Solution

Figure 1

Autism prevalence versus Toxic Release Inventory reported air mercury emissions, with threes substituted for censored values (𝑐=3) for all data points. Lines show the covariate-adjusted random effects Poisson model predictions using five different fixed value substitution approaches (substituting different values of 𝑐 for the censored counts).