Create a display of CWRES diagnostic plots

Get a single graphic of basic CWRES diagnostics (cwres_panel()) or get the component plots in a list that can be arranged by the user (cwres_panel_list()) . See cwres_covariate() for plotting CWRES versus covariates.

cwres_panel(
  df,
  xname = "value",
  unit_time = "hours",
  unit_tad = "hours",
  xby_time = NULL,
  xby_tad = NULL,
  tag_levels = NULL
)

cwres_panel_list(
  df,
  xname = "value",
  unit_time = "hours",
  unit_tad = "hours",
  xby_time = NULL,
  xby_tad = NULL
)

Arguments

df

a data frame to plot.

xname

passed to npde_pred().

unit_time

passed to npde_tad() as xunit.

unit_tad

passed to npde_time() as xunit.

xby_time

passed to npde_time() as xby.

xby_tad

passed to npde_tad() as xby.

tag_levels

passed to patchwork::plot_annotation().

Value

cwres_panel() returns a single graphic with the following panels:

• CWRES versus TIME via cwres_time()

• CWRES versus TAD via cwres_tad()

• CWRES versus PRED via cwres_pred()

• CWRES histogram via cwres_hist()

• CWRES quantile-quantile plot via cwres_q()

cwres_panel_list() returns a list of the individual plots that are incorporated into the cwres_panel() output. Each element of the list is named for the plot in that position: time, tad, pred, hist q. See Examples for how you can work with that list.

See also

npde_panel(), npde_covariate()

Examples

data <- pmplots_data_obs()
cwres_panel(data, tag_levels = "A")
#> `geom_smooth()` using formula = 'y ~ x'
#> `geom_smooth()` using formula = 'y ~ x'
#> `geom_smooth()` using formula = 'y ~ x'
#> `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.


l <- cwres_panel_list(data)
with(l, (q+hist) / pred)
#> `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
#> `geom_smooth()` using formula = 'y ~ x'