Merge pull request #344 from stan-dev/update-psis-paper-reference

update psis paper reference

R/gpd.R

@@ -26,7 +26,7 @@ qgeneralized_pareto <- function(p, mu = 0, sigma = 1, k = 0, lower.tail = TRUE,
 #' 0. By default the fit uses a prior for \eqn{k} (this is in addition to the prior described by Zhang and Stephens, 2009), which will stabilize
 #' estimates for very small sample sizes (and low effective sample sizes in the
 #' case of MCMC samples). The weakly informative prior is a Gaussian prior
-#' centered at 0.5 (see details in Vehtari et al., 2022).
+#' centered at 0.5 (see details in Vehtari et al., 2024).
 #'
 #' @param x A numeric vector. The sample from which to estimate the parameters.
 #' @param wip Logical indicating whether to adjust \eqn{k} based on a weakly
@@ -67,7 +67,7 @@ gpdfit <- function(x, wip = TRUE, min_grid_pts = 30, sort_x = TRUE) {
   sigma_hat <- -k_hat / theta_hat
 
   # adjust k_hat based on weakly informative prior, Gaussian centered on 0.5.
-  # this stabilizes estimates for very small Monte Carlo sample sizes and low neff (see Vehtari et al., 2022 for details)
+  # this stabilizes estimates for very small Monte Carlo sample sizes and low neff (see Vehtari et al., 2024 for details)
   if (wip) {
     k_hat <- (k_hat * N + 0.5 * 10) / (N + 10)
   }

R/pareto_smooth.R

@@ -3,7 +3,7 @@
 #' Estimate Pareto k value by fitting a Generalized Pareto
 #' Distribution to one or two tails of x. This can be used to estimate
 #' the number of fractional moments that is useful for convergence
-#' diagnostics. For further details see Vehtari et al. (2022).
+#' diagnostics. For further details see Vehtari et al. (2024).
 #'
 #' @family diagnostics
 #' @template args-pareto
@@ -91,21 +91,21 @@ pareto_khat.rvar <- function(x, ...) {
 #' Pareto smoothed estimates can be considered reliable. If the actual
 #' sample size is lower than `min_ss`, increasing the sample size
 #' might result in more reliable estimates. For further details, see
-#' Section 3.2.3, Equation 11 in Vehtari et al. (2022).
+#' Section 3.2.3, Equation 11 in Vehtari et al. (2024).
 #'
 #'  * `khat_threshold`: Threshold below which k-hat values result in
 #' reliable Pareto smoothed estimates. The threshold is lower for
 #' smaller effective sample sizes. If k-hat is larger than the
 #' threshold, increasing the total sample size may improve reliability
 #' of estimates. For further details, see Section 3.2.4, Equation 13
-#' in Vehtari et al. (2022).
+#' in Vehtari et al. (2024).
 #'
 #'  * `convergence_rate`: Relative convergence rate compared to the
 #'  central limit theorem. Applicable only if the actual sample size
 #'  is sufficiently large (greater than `min_ss`). The convergence
 #'  rate tells the rate at which the variance of an estimate reduces
 #'  when the sample size is increased, compared to the central limit
-#'  theorem convergence rate. See Appendix B in Vehtari et al. (2022).
+#'  theorem convergence rate. See Appendix B in Vehtari et al. (2024).
 #'
 #' @seealso [`pareto_khat`] for only calculating khat, and
 #'   [`pareto_smooth`] for Pareto smoothed draws.
@@ -177,7 +177,7 @@ pareto_diags.rvar <- function(x, ...) {
 #'
 #' Smooth the tail draws of x by replacing tail draws by order
 #' statistics of a generalized Pareto distribution fit to the
-#' tail(s). For further details see Vehtari et al. (2022).
+#' tail(s). For further details see Vehtari et al. (2024).
 #'
 #' @template args-pareto
 #' @param return_k (logical) Should the Pareto khat be included in

man-roxygen/args-pareto.R

@@ -12,7 +12,7 @@
 #'   `ndraws_tail` is not specified, it will be calculated as
 #'   ceiling(3 * sqrt(length(x) / r_eff)) if length(x) > 225 and
 #'   length(x) / 5 otherwise (see Appendix H in Vehtari et
-#'   al. (2022)).
+#'   al. (2024)).
 #' @param r_eff (numeric) relative effective sample size estimate. If
 #'   `r_eff` is NULL, it will be calculated assuming the draws are
 #'   from MCMC. Default is 1.

man-roxygen/ref-vehtari-paretosmooth-2022.R

@@ -1,4 +1,5 @@
 #' @references
 #' Aki Vehtari, Daniel Simpson, Andrew Gelman, Yuling Yao and
-#' Jonah Gabry (2022). Pareto Smoothed Importance Sampling.
+#' Jonah Gabry (2024). Pareto Smoothed Importance Sampling.
+#' *Journal of Machine Learning Research*, accepted for publication.
 #' arxiv:arXiv:1507.02646 (version 8)