LOO is a common method for evaluating both model fit (LOO-IC analogous to AIC or WAIC) and influential points (pointwise LOO-IC and pareto k LOO-IC evaluation). Methods for both are provided by the loo package. It would be nice to provide wrappers for the loo functions following our API.
Cho, H. (2009). Bayesian influence diagnostic methods for parametric regression models [Doctoral dissertation, University of North Carolina at Chapel Hill]. https://doi.org/10.17615/9sde-5372
LOO is a common method for evaluating both model fit (LOO-IC analogous to AIC or WAIC) and influential points (pointwise LOO-IC and pareto k LOO-IC evaluation). Methods for both are provided by the loo package. It would be nice to provide wrappers for the loo functions following our API.