Aki Vehtari
Aki Vehtari
Add CORP reliability diagrams for classifiers. Calibration plots are highly recommended, and CORP approach is a recent automatic and non-parametric approach I think is making this better than I've seen...
Add calibration plot for binary outcomes using caret::calibration and ggplot See an example in Section "Calibration of predictions" in https://rawgit.com/avehtari/modelselection_tutorial/master/diabetes.html
Running example models gives warning > Warning (non-fatal): assignment operator
On page https://github.com/stan-dev/example-models/wiki/BUGS-Examples-Sorted-Alphabetically under "Stacks: "robust regression"" the link to "Stan code" is https://github.com/stan-dev/example-models/blob/master/bugs_examples/vol1/stacks/stacks.stan which gives 404. Unlike other examples, Stacks has 6 different Stan code files (with different residual...
Pareto-khat diagnostic can be used in general for any Monte Carlo expectation estimate (not just importance sampling) I'm drafting here different functions and their arguments. Some of these are based...
The posterior package started with focus on multi-chain MCMC and stores chain and iterations ids. These are useful when computing multi-chain Rhat, ESS, and MCSE. It is also possible to...
For a very large number of variables stored in csv, it could be useful to use Arrow to read posterior csv as Arrow data table and use that to let...
`?weight_draws` says `Add weights to draws objects, with one weight per draw, for use in subsequent weighting operations.` Currently the only supported subsequent operation is `resample_draws()`, but the documentation doesn't...
Add a diagnostic comparing ESS with all iterations and ESS with half of the iterations (could be average of the first and second half). If CLT holds, then we expect...
In #117 I wrote > I don't know if this would make sense but adding here, that there could be something that would show the mcse in compact format. I...