Allow tidy_draws to work with rstanarm models with a single variable

[damonbayer]

Fixes #331

Proof of the fix:

library(rstanarm)
#> Loading required package: Rcpp
#> This is rstanarm version 2.32.1
#> - See https://mc-stan.org/rstanarm/articles/priors for changes to default priors!
#> - Default priors may change, so it's safest to specify priors, even if equivalent to the defaults.
#> - For execution on a local, multicore CPU with excess RAM we recommend calling
#>   options(mc.cores = parallel::detectCores())
library(tidybayes)

# Simulate some data
true_prob <- 0.25
n <- sample(10:20, 20, replace = TRUE)
y <- rbinom(20, n, true_prob)
dat <- data.frame(hits = y, misses = n - y)

# Fit an intercept-only model
m <- stan_glm(cbind(hits, misses) ~ 1, data = dat, family = binomial())

post <- tidy_draws(m)
post
#> # A tibble: 4,000 × 10
#>    .chain .iteration .draw `(Intercept)` accept_stat__ stepsize__ treedepth__
#>     <int>      <int> <int>         <dbl>         <dbl>      <dbl>       <dbl>
#>  1      1          1     1         -1.22         0.891      0.814           2
#>  2      1          2     2         -1.26         1          0.814           1
#>  3      1          3     3         -1.48         0.905      0.814           1
#>  4      1          4     4         -1.27         0.974      0.814           2
#>  5      1          5     5         -1.29         1          0.814           1
#>  6      1          6     6         -1.27         0.980      0.814           1
#>  7      1          7     7         -1.31         1          0.814           2
#>  8      1          8     8         -1.41         0.969      0.814           2
#>  9      1          9     9         -1.26         0.906      0.814           1
#> 10      1         10    10         -1.57         0.993      0.814           2
#> # ℹ 3,990 more rows
#> # ℹ 3 more variables: n_leapfrog__ <dbl>, divergent__ <dbl>, energy__ <dbl>

^{Created on 2025-03-19 with reprex v2.1.1}

[mbedward]

@damonbayer Just tested this and it is working perfectly for me. Thanks!

[mjskay]

Thanks for this! Is there a fix that doesn't introduce a direct dependency on abind? Might be able to use NROW instead of nrow for the first bit.

[damonbayer]

Thanks @mjskay. I removed the abind dependency in 26db78a (#333).