update doc and snaps

Author: jgabry

DESCRIPTION

@@ -2,7 +2,7 @@ Package: bayesplot
 Type: Package
 Title: Plotting for Bayesian Models
 Version: 1.10.0
-Date: 2022-11-14
+Date: 2022-11-15
 Authors@R: c(person("Jonah", "Gabry", role = c("aut", "cre"), email = "jsg2201@columbia.edu"),
              person("Tristan", "Mahr", role = "aut"),
              person("Paul-Christian", "Bürkner", role = "ctb"),

R/mcmc-traces.R

@@ -66,13 +66,11 @@
 #'   }
 #'   \item{`mcmc_rank_ecdf()`}{
 #'    The ECDFs of the ranks from `mcmc_rank_hist()` are plotted with the
-#'    simultaneous confidence bands with a coverage determined by `prob`,
-#'    that is, bands that completely cover all of the rank ECDFs with the
-#'    probability 'prob'.
-#'    If plot_diff = TRUE, the difference between the observed rank ECDFs and the
-#'    theoretical expectation for samples originating from the same distribution
-#'    is drawn.
-#'    See Säilynoja et al. (2021) for details.
+#'    simultaneous confidence bands with a coverage determined by `prob`, that
+#'    is, bands that completely cover all of the rank ECDFs with the probability
+#'    `prob`. If `plot_diff = TRUE`, the difference between the observed rank
+#'    ECDFs and the theoretical expectation for samples originating from the
+#'    same distribution is drawn. See Säilynoja et al. (2021) for details.
 #'   }
 #' }
 #'
@@ -443,7 +441,7 @@ mcmc_rank_hist <- function(x,
 #' @param prob For `mcmc_rank_ecdf()`, a value between 0 and 1
 #' specifying the desired simultaneous confidence of the confidence bands to be
 #' drawn for the rank ECDF plots.
-#' @param plot_diff For `mcmc_rank_ecdf()`, a boolean specifying it the
+#' @param plot_diff For `mcmc_rank_ecdf()`, a boolean specifying if the
 #' difference between the observed rank ECDFs and the theoretical expectation
 #' should be drawn instead of the unmodified rank ECDF plots.
 #' @export
@@ -456,7 +454,7 @@ mcmc_rank_ecdf <-
            K = NULL,
            facet_args = list(),
            prob = 0.99,
-           plot_diff = TRUE,
+           plot_diff = FALSE,
            interpolate_adj = NULL) {
   check_ignored_arguments(...,
     ok_args = c("K", "pit", "prob", "plot_diff", "interpolate_adj", "M")

R/ppc-distributions.R

@@ -71,10 +71,10 @@
 #' # ppc_ecdf_overlay with continuous data (set discrete=TRUE if discrete data)
 #' ppc_ecdf_overlay(y, yrep[sample(nrow(yrep), 25), ])
 #'
-#' # ECDF and ECDF difference plot of the PIT values of ´y´ compared to ´yrep
+#' # ECDF and ECDF difference plot of the PIT values of y compared to yrep
 #' # with 99% simultaneous confidence bands.
-#' ppc_pit_ecdf(y, yrep, prob = 0.99, plot_diff = FALSE, interpolate_adj = FALSE)
-#' ppc_pit_ecdf(y, yrep, prob = 0.99, plot_diff = TRUE, interpolate_adj = FALSE)
+#' ppc_pit_ecdf(y, yrep, prob = 0.99, plot_diff = FALSE)
+#' ppc_pit_ecdf(y, yrep, prob = 0.99, plot_diff = TRUE)
 #' }
 #'
 #' # for ppc_hist,dens,freqpoly,boxplot definitely use a subset yrep rows so
@@ -107,7 +107,7 @@
 #' \donttest{
 #' # ECDF difference plots of the PIT values by group
 #' # with 99% simultaneous confidence bands.
-#' ppc_pit_ecdf_grouped(y, yrep, group=group, prob=0.99, interpolate_adj=FALSE)
+#' ppc_pit_ecdf_grouped(y, yrep, group=group, prob=0.99, plot_diff = TRUE)
 #' }
 #'
 #' # don't need to only use small number of rows for ppc_violin_grouped
@@ -580,8 +580,8 @@ ppc_violin_grouped <-
 
 #' @export
 #' @param pit An optional vector of probability integral transformed values for
-#' which the ECDF is to be drawn. If NULL, PIT values are computed to ´y´ with
-#' respect to the corresponding values in ´yrep´.
+#'   which the ECDF is to be drawn. If NULL, PIT values are computed to `y` with
+#'   respect to the corresponding values in `yrep`.
 #' @rdname PPC-distributions
 #'
 ppc_pit_ecdf <- function(y,

man-roxygen/args-pit-ecdf.R

@@ -1,12 +1,16 @@
 #' @param K An optional integer defining the number of equally spaced evaluation
-#' points for the ECDF. If the submitted PIT values are known to be discrete,
-#' this should be the number of the discrete cases. Defaults to the smaller of
-#' `length(y)` and `ncol(yrep)` when applicable.
+#'   points for the ECDF. If the submitted PIT values are known to be discrete,
+#'   this should be the number of the discrete cases. Defaults to the smaller of
+#'   `length(y)` and `ncol(yrep)` when applicable.
 #' @param prob The desired simultaneous coverage level of the bands around the
-#' ECDF. A value in (0,1).
-#' @param plot_diff A boolean defining whether to plot the difference between the
-#' observed ECDF and the theoretical expectation for uniform PIT values.
+#'   ECDF. A value in (0,1).
+#' @param plot_diff A boolean defining whether to plot the difference between
+#'   the observed ECDF and the theoretical expectation for uniform PIT values
+#'   rather than plotting the regular ECDF. The default is `FALSE`, but for
+#'   large samples we recommend setting `plot_diff=TRUE` as the difference plot
+#'   will visually show a more dynamic range.
 #' @param interpolate_adj A boolean defining if the simultaneous confidence
-#' bands should be computed or interpolated from precomputed values. Computing
-#' the bands may be computationally intensive and approximation gives a fast
-#' method for assessing the ECDF trajectory.
+#'   bands should be interpolated based on precomputed values rather than
+#'   computed exactly. Computing the bands may be computationally intensive and
+#'   the approximation gives a fast method for assessing the ECDF trajectory.
+#'   The default is to use interpolation if `K` is greater than 200.