bland_altman: Bland-Altman agreement plots.

In pubh: A Toolbox for Public Health and Epidemiology

Bland-Altman agreement plots.

Description

Bland-Altman agreement plots.

Usage

bland_altman(
  object = NULL,
  formula = NULL,
  data = NULL,
  pch = 20,
  size = 1,
  col = "black",
  transform = FALSE,
  ...
)

Arguments

object	When chaining, this holds an object produced in the earlier portions of the chain. Most users can safely ignore this argument. See details and examples.
formula	A formula with shape: y ~ x (see details).
data	A data frame where the variables in the formula can be found.
pch	Symbol for plotting data.
size	Size of the symbol using to plot data.
col	Colour used for the symbol to plot data.
transform	Logical, should ratios instead of difference be used to construct the plot?
...	Further arguments passed to gf_point.

Details

bland_altman constructs Bland-Altman agreement plots.

Variables in formula are continuous paired observations. When the distribution of the outcome is not normal, but becomes normal with a log-transformation, bland_altman can plot the ratio between outcomes (difference in the log scale) by using option transform = TRUE.

Examples

data(wright, package = "ISwR")

wright |>
  bland_altman(mini.wright ~ std.wright,
    pch = 16,
    ylab = "Large-mini expiratory flow rate (l/min)",
    xlab = "Mean expiratory flow rate (l/min)"
  ) |>
  gf_labs(
    y = "Large-mini expiratory flow rate (l/min)",
    x = "Mean expiratory flow rate (l/min)"
  )

data(Sharples)

Sharples |>
  bland_altman(srweight ~ weight, transform = TRUE) |>
  gf_labs(x = "Mean of weights (kg)", y = "Measured weight / Self-reported weight")

pubh documentation built on Oct. 8, 2024, 9:08 a.m.