forest.cdmeta: Forest plot for cdmeta objects

In cdmeta: Confidence-Distribution-Based Inference for Random-Effects Meta-Analysis

Forest plot for cdmeta objects

Description

Draws a forest plot from an object of class "cdmeta". The plot shows study-specific effect estimates and confidence intervals, the confidence-distribution-based summary estimate for the overall mean effect, and optionally the prediction interval for the effect in a future study.

Usage

## S3 method for class 'cdmeta'
forest(
  x,
  slab = NULL,
  order = c("none", "increasing", "decreasing", "precision", "weight"),
  level = NULL,
  summary_stat = c("mean", "median"),
  refline = 0,
  xlab = "Effect size",
  main = NULL,
  atransf = NULL,
  at = NULL,
  alim = NULL,
  xlim = NULL,
  digits = 2,
  ci_digits = digits,
  weight_digits = 1,
  show_weights = TRUE,
  show_pi = TRUE,
  show_het = TRUE,
  header = TRUE,
  annotate = TRUE,
  cex = 0.85,
  psize = NULL,
  pch = 22,
  box_col = "black",
  box_bg = "white",
  ci_col = "black",
  summary_col = "black",
  summary_bg = "gray20",
  pi_col = "gray40",
  refline_col = "gray70",
  grid = TRUE,
  grid_col = "gray90",
  qtype = 8,
  symmetric_shapes = TRUE,
  mark_summary_estimate = FALSE,
  mark_prediction_estimate = FALSE,
  estimate_mark_col = "black",
  estimate_mark_lwd = 1,
  mar = c(4.5, 1, 3, 1),
  ...
)

forest(x, ...)

Arguments

x	An object of class "cdmeta".
slab	An optional character vector of study labels. If NULL, the names of x$data$y are used when available; otherwise generic study labels are created.
order	A character string specifying the order of studies in the plot. Available options are "none", "increasing", "decreasing", "precision", and "weight".
level	Confidence level used for study-specific and summary intervals. If NULL, 1 - x$alpha is used.
summary_stat	Whether Monte Carlo means ("mean") or medians ("median") are used as point estimates for summary rows.
refline	Numeric location of the reference line.
xlab	Label for the x-axis.
main	Optional main title.
atransf	Optional function used to transform axis labels and printed estimates while plotting coordinates remain on the original analysis scale.
at	Optional numeric vector specifying tick-mark locations on the original analysis scale.
alim	Optional numeric vector of length 2 specifying plotting limits for the effect-size axis on the original analysis scale.
xlim	Optional numeric vector of length 2 specifying full plotting limits including the text columns.
digits	Number of digits used for axis labels.
ci_digits	Number of digits used for effect estimates and intervals.
weight_digits	Number of digits used for study weights.
show_weights	Logical indicating whether study weights are shown.
show_pi	Logical indicating whether the prediction interval is shown.
show_het	Logical indicating whether heterogeneity statistics are shown.
header	Logical indicating whether column headers are shown.
annotate	Logical indicating whether estimates and intervals are printed on the right side of the plot.
cex	Character expansion factor.
psize	Optional point sizes for study-specific estimates. If NULL, point sizes are proportional to random-effects inverse-variance weights.
pch	Plotting symbol for study-specific estimates.
box_col	Border color of study-specific points.
box_bg	Fill color of study-specific points.
ci_col	Color of study-specific confidence intervals.
summary_col	Border color of the summary diamond.
summary_bg	Fill color of the summary diamond.
pi_col	Color of the prediction interval.
refline_col	Color of the reference line.
grid	Logical indicating whether vertical grid lines are drawn.
grid_col	Color of the grid lines.
qtype	Quantile type used in stats::quantile(). Default is 8.
symmetric_shapes	Logical indicating whether the summary diamond and prediction-interval marker are drawn symmetrically around interval midpoints.
mark_summary_estimate	Logical indicating whether the actual summary point estimate is marked inside the summary diamond.
mark_prediction_estimate	Logical indicating whether the actual predictive point estimate is marked on the prediction-interval row.
estimate_mark_col	Color of the actual-estimate marks.
estimate_mark_lwd	Line width of the actual-estimate marks.
mar	Plot margins passed to graphics::par().
...	Additional arguments passed to graphics::plot().

Details

Study-specific confidence intervals are calculated using the normal approximation

y_i \pm z_{1-\alpha/2} se_i,

where \alpha = 1 - level. The summary interval for \mu and the prediction interval are calculated from the Monte Carlo samples in the cdmeta object when available.

If the object was created with transf = exp, forest() uses this transformation automatically when atransf = NULL. Tick marks supplied through at remain on the original analysis scale.

Value

Invisibly returns a data frame containing the plotted study-specific estimates, standard errors, confidence intervals, and weights. Attributes contain the overall, prediction, and heterogeneity summaries on the original analysis scale.

See Also

cdmeta

Examples

data(hf_iron)
fit_hf <- cdmeta(
  y = hf_iron$yi,
  se = hf_iron$sei,
  B = 10000,
  seed = 11111,
  transf = exp,
  transf_name = "exp"
)

forest(
  fit_hf,
  slab = hf_iron$study,
  at = log(c(0.25, 0.5, 1, 2, 4)),
  xlab = "Risk ratio",
  mark_summary_estimate = TRUE,
  mark_prediction_estimate = TRUE
)

cdmeta documentation built on Sept. 15, 2026, 5:09 p.m.