In the example model page, the regularised horseshoe prior is given as follows as per Piironen & Vehtari (2017) *Electronic Journal of Statistics*:

```
regularized_horseshoe <- function (tau = 1, c = 1, dim = NULL) {
stopifnot(c > 0)
lambda <- cauchy(0, 1, truncation = c(0, Inf), dim = dim)
lambda_tilde <- (c^2 * lambda^2) / (c^2 + tau^2 * lambda^2)
sd <- tau ^ 2 * lambda_tilde ^ 2
normal(0, sd, dim = dim)
}
```

However, Piironen & Vehtari (2017) seems to denote `tau ^ 2 * lambda_tilde ^ 2`

as variance `sd^2`

. If this is true, should the penultimate line be `sd <- tau * lambda_tilde`

instead?