Jonah Gabry

Use posterior::autocovariance() once on CRAN

5

Remember to replace the short term fix for issue #151 (in PR #155) by using `posterior::autocovariance()` once the posterior package is on CRAN. This will avoid having to maintain the...

Averaging predictive distributions

9

This is related to #82 but should be it’s own issue. Currently we rely on users to use the model weights to create the appropriate mixture of predictive distributions. We...

Subsetting psis objects

3

The PR introduces a `subset()` method for `"psis"` objects. This is useful if you want to drop some of the contents of a `"psis"` object without breaking it. For example,...

Convenience functions for accessing pointwise estimates

1

Right now to get the pointwise values for elpd_loo, p_loo, etc., you have to do this: ```r object$pointwise[, "elpd_loo"] ``` but it would be nice if we offered a convenience...

plot method for two loo objects

1

We should have a plotting method (in loo or bayesplot) that creates the pointwise elpd difference plot from Figure 10a of [Visualization in Bayesian Workflow](https://arxiv.org/abs/1709.01449)

Don't require two Stan programs to use standalone GQs (add a flag to services to turn off GQ block)

4

#### Summary: This came up when @rok-cesnovar and I were discussing the PR to add standalone generated quantities to CmdStanR: Using standalone generated quantities requires the user to keep two...

Provide access to initial values

11

We've recently discussed how CmdStan does not have a way to provide users access to the initial values it used: * https://discourse.mc-stan.org/t/does-the-init-argument-work-with-cmdstanr/17255/19 * https://github.com/stan-dev/cmdstan/issues/918 It sounds like this is actually...

optimizing needs informative error message if theta_tilde not returned

1

For `optimizing`, when this line https://github.com/stan-dev/rstan/blob/322a3e8e0567e775dde97c80986463e46649e59b/rstan/rstan/R/stanmodel-class.R#L369 is executed, if `is.matrix(R

#### Summary: `read_csv_header`, which is called internally by `read_stan_csv`, will fail if the model name contains the string `"thin"` anywhere. In an example on the forums reported by @sdaza the...

Originally pointed out on the forum in https://discourse.mc-stan.org/t/why-does-stan-lm-ignore-a-factor-level-in-a-model-with-no-intercept/24877. @bgoodri `stan_lm` still drops a factor level even if the intercept is omitted, e.g. `stan_lm(mpg ~ 0 + as.factor(cyl), data = mtcars,...