Skip to contents

Plot the full distribution of network treatment ranks

Usage

network_rank_plot(
  object,
  benefit_direction,
  strata = NULL,
  nsim = 10000L,
  seed = 1L,
  main = "Treatment rank probabilities",
  colors = c("#F7FBFF", "#0072B2"),
  type = c("heatmap", "bar"),
  label_cex = 0.8,
  value_cex = 0.8
)

Arguments

object

A fitted network model; for the ranking-table summary method, the rankings data frame returned by network_rankings().

benefit_direction

Whether higher or lower effects are preferable.

strata

Named outcome/time selection; exactly one stratum is required.

nsim

Number of draws, at least 100.

seed

Optional local seed; the caller's random-number state is restored.

main

Plot title.

colors

Heatmap palette; the last color is used for bar rankograms.

type

heatmap (default) compares all treatments and ranks together; bar draws one rankogram panel per treatment with a common probability axis.

label_cex

Scaling for treatment/axis labels. Font family and style inherit base graphics settings such as par(family="sans", font=1).

value_cex

Scaling for heatmap probability labels.

Value

Invisibly returns the ranking calculation, including benefit direction.

Details

Both displays use the same joint simulations and return the same ranking object. The heatmap shows rank 1 on the left, treatments ordered by mean rank (best average position first), a fixed 0–1 color scale and rounded percentage labels. Bar panels show rank on the horizontal axis and its probability on the vertical axis, with treatments in the same mean-rank order. Each panel sums to one for continuous draws without ties. A sharply concentrated distribution indicates a more certain rank under this model; a broad or multi-peaked distribution is hidden by a single SUCRA summary. These plots concern ranks of average effects, not effect magnitudes, clinical relevance or new-study predictions. Zero-percent heatmap labels can represent small nonzero probabilities after rounding.

References

Rücker, G., and Schwarzer, G. (2015). Ranking treatments in frequentist network meta-analysis works without resampling methods. BMC Medical Research Methodology, 15, 58. doi:10.1186/s12874-015-0060-8 .

Salanti, G., Ades, A. E., and Ioannidis, J. P. A. (2011). Graphical methods and numerical summaries for presenting results from multiple-treatment meta-analysis: an overview and tutorial. Journal of Clinical Epidemiology, 64, 163–171. doi:10.1016/j.jclinepi.2010.03.016 .

See also

network_rankings() for joint simulation and ranking definitions.

Examples

dat <- data.frame(study = 1:6, a = rep(c("A", "A", "B"), 2),
                  b = rep(c("B", "C", "C"), 2),
                  yi = c(.2, .5, .3, .3, .6, .4), vi = .04)
fit <- network_meta(dat, "study", "a", "b", "yi", "vi")
network_rank_plot(fit, benefit_direction = "higher", nsim = 500)