Cost-effectiveness plane

Introduction

The intention of this vignette is to show how to plot different styles of cost-effectiveness acceptability curves using the BCEA package.

R code

To calculate these in BCEA we use the bcea() function.

data("Vaccine")

he <- bcea(eff, cost)
#> No reference selected. Defaulting to first intervention.

The plot defaults to base R plotting. Type of plot can be set explicitly using the graph argument.

ceplane.plot(he, graph = "base")

ceplane.plot(he, graph = "ggplot2")

# ceac.plot(he, graph = "plotly")

Other plotting arguments can be specified such as title, line colours and theme.

ceplane.plot(he,
             graph = "ggplot2",
             title = "my title",
             line = list(color = "green", size = 3),
             point = list(color = "blue", shape = 10, size = 5),
             icer = list(color = "orange", size = 5),
             area = list(fill = "grey"),
             theme = theme_linedraw())

If you only what the mean point then you can suppress the sample points by passing size NA.

ceplane.plot(he,
             graph = "ggplot2",
             point = list(size = NA),
             icer = list(size = 5))
#> Warning: Removed 1000 rows containing missing values or values outside the scale range
#> (`geom_point()`).

Multiple interventions

This situation is when there are more than two interventions to consider.

R code

data("Smoking")

he <- bcea(eff, cost, ref = 4)
# str(he)

Basic plots with defaults.

ceplane.plot(he)

ceplane.plot(he, graph = "ggplot2")

The font size can be adjusted using the text argument.

ceplane.plot(he, graph = "ggplot2", text = list(size = 20))

ceplane.plot(he, graph = "ggplot2", text = list(size = rel(2)))  # relative scaling, double size


# equivalent but more flexible and direct
ceplane.plot(he, graph = "ggplot2") +
  theme(axis.text = element_text(size = 18),
        axis.title.x = element_text(size = 20),
        axis.title.y = element_text(size = 20))

Numerous different styling arguments can be provided.

ceplane.plot(he,
             graph = "ggplot2",
             title = "my title",
             line = list(color = "red", size = 1),
             point = list(color = c("plum", "tomato", "springgreen"), shape = 3:5, size = 2),
             icer = list(color = c("red", "orange", "black"), size = 5))

There are various different ways to reposition the legend.

ceplane.plot(he, pos = FALSE) # bottom right

ceplane.plot(he, pos = c(0, 0))

ceplane.plot(he, pos = c(0, 1))

ceplane.plot(he, pos = c(1, 0))

ceplane.plot(he, pos = c(1, 1))

Willingness-to-pay label

For {ggplot2} we can modify the willingness-to-pay label e.g. “k = 25000”.

The default is

ceplane.plot(he, graph = "ggplot2")

The simplest argument is to set the value of the willingness-to-pay threshold using wtp.

ceplane.plot(he, graph = "ggplot2", wtp = 10000)

Alternatively, we can pass a list of arguments to wtp to modify the appearance of the label.

ceplane.plot(he, graph = "ggplot2", wtp = list(value = 10000))

ceplane.plot(he, graph = "ggplot2", wtp = list(value = 10000, colour = "blue"))

ceplane.plot(he, graph = "ggplot2", wtp = list(colour = "blue"))

ceplane.plot(he, graph = "ggplot2", wtp = list(size = 5))

To hide the text assign size = 0.

ceplane.plot(he, graph = "ggplot2", wtp = list(size = 0))

The label is placed at the left hand side of the plot next to the willingness-to-pay line by default. When this would mean the label is off the bottom of the plot it is positioned at the bottom left corner.

data("Vaccine")
he <- bcea(eff, cost, ref=2)

ceplane.plot(he, graph = "ggplot2")

ceplane.plot(he, graph = "ggplot2", wtp = 1000, xlim = c(-0.0005, 0.0015))

ceplane.plot(he, graph = "ggplot2", wtp = 10000, xlim = c(-0.0005, 0.0015))

ceplane.plot(he, graph = "ggplot2", wtp = 25000, xlim = c(-0.0005, 0.0015))

ceplane.plot(he, graph = "ggplot2", wtp = 50000, xlim = c(-0.0005, 0.0015))

The position of the label can be adjusted using the label.pos argument and a logical value.

ceplane.plot(he, graph = "ggplot2", wtp = 1000, xlim = c(-0.0005, 0.0015), label.pos = TRUE)

ceplane.plot(he, graph = "ggplot2", wtp = 1000, xlim = c(-0.0005, 0.0015), label.pos = FALSE)

A direct way of specifying the position of the label is to use the wtp argument and set the y value in a list.

ceplane.plot(he, graph = "ggplot2", wtp = list(y = 8))

For base R

ceplane.plot(he)  # default

ceplane.plot(he, wtp = 1000, xlim = c(-0.0005, 0.0015))

ceplane.plot(he, wtp = 10000, xlim = c(-0.0005, 0.0015))

ceplane.plot(he, wtp = 25000, xlim = c(-0.0005, 0.0015))

ceplane.plot(he, wtp = 50000, xlim = c(-0.0005, 0.0015))

ceplane.plot(he, wtp = 1000, xlim = c(-0.0005, 0.0015), label.pos = TRUE)

ceplane.plot(he, wtp = 1000, xlim = c(-0.0005, 0.0015), label.pos = FALSE)

##TODO: not yet implemented ggplot syntax for base R

# ceplane.plot(he, wtp = list(value = 10000))
# ceplane.plot(he, wtp = list(value = 10000, colour = "blue"))
# ceplane.plot(he, wtp = list(colour = "blue"))
# ceplane.plot(he, wtp = list(y = 8))
# ceplane.plot(he, wtp = list(size = 5))
# 
# # to hide text
# ceplane.plot(he, wtp = list(size = 0))