Skip to contents

Create NPDE versus covariate displays

Source: R/displays.R
npde_covariate.Rd

Get a single graphic of NPDE versus continuous and / or categorical covariates (npde_covariate()) or get a list that can be arranged by the user (npde_covariate_list()). See npde_panel() for other NPDE diagnostic displays.

Usage

npde_covariate(df, x, ncol = 2, tag_levels = NULL, byrow = NULL, points = NULL)

npde_covariate_list(df, x, points = NULL)

Arguments

df

a data frame to plot.

x

character col//title for covariates to plot on x-axis; see col_label().

ncol

passed to pm_grid().

tag_levels

passed to patchwork::plot_annotation().

byrow

passed to pm_grid().

points

passed to boxwork() when plotting categorical covariates.

Value

npde_covariate() returns single graphic of scatter plot diagnostics as a patchwork object that has been arranged using pm_grid() and npde_covariate_list() returns the same component plots unarranged in a list.

Details

Pass ncol = NULL or another non-numeric value to bypass arranging plots coming from npde_covariate().

See also

cwres_covariate(), eta_covariate()

Examples

data <- pmplots_data_id()
cont <- c("WT//Weight (kg)", "ALB//Albumin (mg/dL)")
cats <- c("RF//Renal function", "CPc//Child-Pugh")

npde_covariate(data, x = c(cont, cats), tag_levels = "A")
#> `geom_smooth()` using formula = 'y ~ x'
#> `geom_smooth()` using formula = 'y ~ x'

npde_covariate_list(data, x = cats)
#> $RF

#> 
#> $CPc

#> 
#> attr(,"class")
#> [1] "pm_display" "list"