Carlos Parada
Carlos Parada
Specifically, under 100% strategic voting, majority judgment has 0.851 VSE vs 0.947 for approval. But isn't majority judgment identical to approval when all voters are strategic?
Could we get some confidence intervals plotted on the graphs? Some of these results look a bit funky. (Most notably, some methods seem to outperform score under "100% honest" voting,...
Is there a way to download a whole time series from ICPSR, i.e. including several datasets?
Will probably do this when I'm working on k-fold cross-validation, which will be much cleaner with the new `SimpleVarInfo`.
DimensionalData.jl takes ~.15s to load in Julia 1.7, relative to the ~1.5s taken by AxisKeys; switching should cut out most of the compilation time for ParetoSmooth.jl.
Would be nice to make sure PRs don't degrade performance as part of our tests; no idea how this would be done but there's probably some way to go about...
Would be nice to have a way to easily refit folds with high Pareto k values. Mentioning @sethaxen because I know ArviZ.jl has this set up; do you know how/if...
Currently, only Turing is supported; support for Stan, Soss, and Gen would be great.
It would be nice to connect ParetoSmooth to the Turing ecosystem of importance samplers/variational inference, so that PSIS can be used as a step in Sequential Monte Carlo or Variational...