-
Dear Russell,
Hope you are having a great summer. Maybe my following question should be addressed to the authors of Rstan / rstanarm, but I will post it regardless, in case it is helpful.
I notic…
-
-
#### Summary:
In the latest release to 2.19.2 the introduction of the compound glm functions (e.g. bernoulli_logit_glm, poisson_log_glm) to the Stan code has introduced a bug where
intercept only…
-
#### Summary:
When fitting models using `stan_glmer()`, `summary(stan_glmer())` names the elements of the covariance matrix using terms like `Sigma[group:(Intercept),(Intercept)]`. **Especially in t…
-
#### Summary:
Attempts to use `reloo()` called via `loo(...,k_threshold=...)` with a `stan_clogit()` object produce an error.
#### Description:
When I call `loo()` on an object created with `sta…
-
Hello,
after fitting a hierarchical model, results seem relatively ok (few divergences but n_eff adn Rhat seem fine), but I get the following error:
```R
Error in tmp$r_vals[lr - 1] * tmp$r_vals…
-
## Description
When `X` has `0` columns, `beta` has `0` elements, and alpha has `1` element functions like `bernoulli_logit_glm_lpmf` (I've checked poisson too but not others yet) ignore `alpha` an…
-
# Features
## Plan
- [x] generalise `p values`
- [x] generalise `ci`
- [ ] Check that it works for rstanarm and brms models
- [ ] Check that it works for frequentist models
## Optional (pos…
-
Following the code in [Correlation and regression fundamentals with tidy data principles](https://www.tidymodels.org/learn/statistics/tidy-analysis/), I'm not able to replicate the nested output shown…
-
#### Summary:
The documentation asserts that default degrees of freedom for `hs` and `hs_plus` are 3, but in the code they are actually set to 1.
#### RStanARM Version:
git repository