Fig. 9

Posterior probability distribution (density) plots for the model predicting teacher self-efficacy by participation in any induction activities at current school. United States sample. The plots for the regression coefficients and correlations should exhibit more or less a bell-shaped curve while the plot for the variance terms should exhibit a long tail and will be bounded below at zero. The posterior distribution of the effect associated with \(t3jobsa_{ij}\) is not as symmetric as desired. This could be improved by increasing the number of MCMC iterations. We also note that the correlation between the error terms of the intercept and slope equations, Sigma[idschool:induction,(Intercept)], is very small