Diagnostics for the Von Bertalanffy model

Rhat

Divergent transitions

Posterior distribution of parameters

Correlation between parameters

Correlation between Lo parameter and start size data

Data distribution

Predictions

Out-of-bag cross-validation

To assess model generality we test how good the model is in predicting new observations. The following figures show a 1:1 plot of observed vs predicted data for two diferent measures: DBH size (directly predicted by the model) and annual growth rate (derived from predicted size). We also plot the distribution of the observed vs the predicted measures.

Mean squared error (MSE) of out-of-bag predictions

Rsquared

The distribution of R squared values is calculated using the Gelman et al. 2018 definition.

We also calculated the \(R^2\) from the linear model using the 1:1 plot comparing observed values to the predicted values. This approach was used for the size predictions from the model, and the growth predictions derived from the size predictions.

Leave-one-out cross-validation to compare models

Sampling time