Compare estimates from several models or sources

Overlays the estimates from two or more models (or tidy estimate tables) on a single forest plot, with one colour per source. It is the general engine behind frequentist_bayesian_plot() (frequentist against Bayesian), and serves equally well for comparing nested models, several optimisers, or estimates before and after a transformation.

Usage

compare_models(
  ...,
  names = NULL,
  conf_level = 0.95,
  intercept = FALSE,
  order = c("none", "ascending", "descending"),
  labels = NULL,
  interaction = c("times", "asterisk", "colon", "space"),
  dodge_width = 0.6,
  reference_line = if (exponentiate) 1 else 0,
  palette = NULL,
  point_size = 2.2,
  line_size = 0.7,
  facet = FALSE,
  scales = c("fixed", "free"),
  exponentiate = FALSE,
  legend_title = "Source",
  legend_ncol = 1,
  title = NULL,
  subtitle = NULL,
  x_lab = NULL
)

Arguments

...: Two or more fitted models and/or tidy data frames of estimates. Name the arguments to label the sources (e.g. compare_models(Frequentist = m1, Bayesian = m2)).
names: Optional character vector of source labels, overriding the names of ....
conf_level: Confidence/credible level for models, a single number strictly between 0 and 1.
intercept: Whether to keep the intercept term. Defaults to FALSE.
order: Order of the terms, by their average estimate across sources. "ascending" puts the smallest estimate at the bottom and the largest at the top, so estimates increase up the axis. "descending" does the reverse, and "none" keeps the terms in the order they first appear, from top to bottom. The faceted layout (facet = TRUE) stacks its panels the other way up.
labels: Optional display labels. An unnamed vector gives one label per term, whatever order is. The terms are taken in the order they first appear across the sources, each source in the order tidy_estimates() returns, after the intercept is dropped unless intercept = TRUE. Terms drawn on one row, such as stress and brms's b_stress, take one label. A named vector mapping raw term names to labels, such as c(soil_ph = "Soil pH"), is safer. If NULL, the terms are labelled as in coefficient_plot(), each factor level with its variable and level (treatment: enhanced), from every fitted model among the sources.
interaction: Passed to format_terms().
dodge_width: Vertical spacing between sources sharing a term.
reference_line: Position of a vertical reference line. Defaults to 0, or to 1 when exponentiate = TRUE. Use NA to omit it.
palette: Colours for the sources; defaults to depictr_palette().
point_size, line_size: Point and interval-line sizes.
facet: Whether to give each term its own panel with a free x-axis, laid out one per row, so that terms on very different scales (for example a large intercept alongside small slopes) stay legible. The source overlay and its single legend are preserved within the faceted layout. Defaults to FALSE. A convenience alias for scales = "free".
scales: Either "fixed" (the default, a single shared x-axis) or "free" (one free-scaled panel per term). When facet = TRUE this is forced to "free".
exponentiate: Whether to draw every source's exponentiated estimates and intervals on a log10 axis, as odds or rate ratios. Each model is exponentiated by tidy_estimates(), and a data frame among the sources must hold estimates on the link scale, since it is exponentiated too. Defaults to FALSE.
legend_title, legend_ncol: Legend title and number of columns.
title, subtitle, x_lab: Title, subtitle and x-axis label. x_lab defaults to "Estimate". With exponentiate = TRUE it defaults to the name of the ratio, as in coefficient_plot(), when the fitted models agree on it, and to "exp(Estimate)" when they do not.

Value

A ggplot2::ggplot object.

Examples

m1 <- lm(yield ~ rainfall + fertiliser + soil_ph, data = crop_yield)
m2 <- lm(yield ~ rainfall + fertiliser + soil_ph,
         data = crop_yield[crop_yield$treatment == "standard", ])
compare_models(`All fields` = m1, `Standard only` = m2,
                       title = "Estimates by subset")


# Keep the intercept legible alongside the slopes:
compare_models(`All fields` = m1, `Standard only` = m2,
               intercept = TRUE, facet = TRUE)


# Odds ratios from two logistic regressions:
g1 <- glm(accuracy ~ word_frequency + condition,
          data = lexical_decision, family = binomial)
g2 <- glm(accuracy ~ word_frequency + condition + modality,
          data = lexical_decision, family = binomial)
compare_models(Reduced = g1, Full = g2, exponentiate = TRUE)