Package 'modelsummary' reference manual

Title:	Summary Tables and Plots for Statistical Models and Data: Beautiful, Customizable, and Publication-Ready
Description:	Create beautiful and customizable tables to summarize several statistical models side-by-side. Draw coefficient plots, multi-level cross-tabs, dataset summaries, balance tables (a.k.a. "Table 1s"), and correlation matrices. This package supports dozens of statistical models, and it can produce tables in HTML, LaTeX, Word, Markdown, PDF, PowerPoint, Excel, RTF, JPG, or PNG. Tables can easily be embedded in 'Rmarkdown' or 'knitr' dynamic documents. Details can be found in Arel-Bundock (2022) <doi:10.18637/jss.v103.i01>.
Authors:	Vincent Arel-Bundock [aut, cre, cph] , Joachim Gassen [ctb] , Nathan Eastwood [ctb], Nick Huntington-Klein [ctb] , Moritz Schwarz [ctb] , Benjamin Elbers [ctb] (0000-0001-5392-3448), Grant McDermott [ctb] , Lukas Wallrich [ctb]
Maintainer:	Vincent Arel-Bundock <[email protected]>
License:	GPL-3
Version:	2.2.0.4
Built:	2024-11-21 01:28:31 UTC
Source:	https://github.com/vincentarelbundock/modelsummary

Rename model terms

Description

A convenience function which can be passed to the coef_rename argument of the modelsummary function.

Usage

coef_rename(
  x,
  factor = TRUE,
  factor_name = TRUE,
  poly = TRUE,
  backticks = TRUE,
  titlecase = TRUE,
  underscore = TRUE,
  asis = TRUE
)
coef_rename(
  x,
  factor = TRUE,
  factor_name = TRUE,
  poly = TRUE,
  backticks = TRUE,
  titlecase = TRUE,
  underscore = TRUE,
  asis = TRUE
)

Arguments

`x`	character vector of term names to transform
`factor`	boolean remove the "factor()" label
`factor_name`	boolean remove the "factor()" label and the name of the variable
`poly`	boolean remove the "poly()" label and function arguments
`backticks`	boolean remove backticks
`titlecase`	boolean convert to title case
`underscore`	boolean replace underscores by spaces
`asis`	boolean remove the `I` from as-is formula calls

Examples

library(modelsummary)
dat <- mtcars
dat$horse_power <- dat$hp
mod <- lm(mpg ~ horse_power + factor(cyl), dat)
modelsummary(mod, coef_rename = coef_rename)

Persistent user settings for the `modelsummary` package

Description

Persistent user settings for the modelsummary package

Usage

config_modelsummary(
  factory_default,
  factory_latex,
  factory_html,
  factory_markdown,
  startup_message,
  reset = FALSE
)
config_modelsummary(
  factory_default,
  factory_latex,
  factory_html,
  factory_markdown,
  startup_message,
  reset = FALSE
)

Arguments

`factory_default`	Default output format: "tinytable", "kableExtra", "gt", "flextable", "huxtable", "DT", or "markdown"
`factory_latex`	Name of package used to generate LaTeX output when `output="latex"`.
`factory_html`	Name of package used to generate LaTeX output when `output="html"`.
`factory_markdown`	Name of package used to generate LaTeX output when `output="markdown"`.
`startup_message`	TRUE or FALSE to show warnings at startup
`reset`	TRUE to return to default settings.

Summary tables using 2-sided formulae: crosstabs, frequencies, table 1s and more.

Description

datasummary can use any summary function which produces one numeric or character value per variable. The examples section of this documentation shows how to define custom summary functions.

modelsummary also supplies several shortcut summary functions which can be used in datasummary() formulas: Min, Max, Mean, Median, Var, SD, NPercent, NUnique, Ncol, P0, P25, P50, P75, P100.

See the Details and Examples sections below, and the vignettes on the modelsummary website:

https://modelsummary.com/
https://modelsummary.com/articles/datasummary.html

Usage

datasummary(
  formula,
  data,
  output = "default",
  fmt = 2,
  title = NULL,
  notes = NULL,
  align = NULL,
  add_columns = NULL,
  add_rows = NULL,
  sparse_header = TRUE,
  escape = TRUE,
  ...
)
datasummary(
  formula,
  data,
  output = "default",
  fmt = 2,
  title = NULL,
  notes = NULL,
  align = NULL,
  add_columns = NULL,
  add_rows = NULL,
  sparse_header = TRUE,
  escape = TRUE,
  ...
)

Arguments

`formula`	A two-sided formula to describe the table: rows ~ columns. See the Examples section for a mini-tutorial and the Details section for more resources. Grouping/nesting variables can appear on both sides of the formula, but all summary functions must be on one side.
`data`	A data.frame (or tibble)
`output`	filename or object type (character string) Supported filename extensions: .docx, .html, .tex, .md, .txt, .csv, .xlsx, .png, .jpg Supported object types: "default", "html", "markdown", "latex", "latex_tabular", "typst", "data.frame", "tinytable", "gt", "kableExtra", "huxtable", "flextable", "DT", "jupyter". The "modelsummary_list" value produces a lightweight object which can be saved and fed back to the `modelsummary` function. The "default" output format can be set to "tinytable", "kableExtra", "gt", "flextable", "huxtable", "DT", or "markdown" If the user does not choose a default value, the packages listed above are tried in sequence. Session-specific configuration: `options("modelsummary_factory_default" = "gt")` Persistent configuration: `config_modelsummary(output = "markdown")` Warning: Users should not supply a file name to the `output` argument if they intend to customize the table with external packages. See the 'Details' section. LaTeX compilation requires the `booktabs` and `siunitx` packages, but `siunitx` can be disabled or replaced with global options. See the 'Details' section.
`fmt`	how to format numeric values: integer, user-supplied function, or `modelsummary` function. Integer: Number of decimal digits User-supplied functions: Any function which accepts a numeric vector and returns a character vector of the same length. `modelsummary` functions: `fmt = fmt_significant(2)`: Two significant digits (at the term-level) `fmt = fmt_sprintf("%.3f")`: See `?sprintf` `fmt = fmt_identity()`: unformatted raw values
`title`	string. Cross-reference labels should be added with Quarto or Rmarkdown chunk options when applicable. When saving standalone LaTeX files, users can add a label such as `⁠\\label{tab:mytable}⁠` directly to the title string, while also specifying `escape=FALSE`.
`notes`	list or vector of notes to append to the bottom of the table.
`align`	A string with a number of characters equal to the number of columns in the table (e.g., `align = "lcc"`). Valid characters: l, c, r, d. "l": left-aligned column "c": centered column "r": right-aligned column "d": dot-aligned column. For LaTeX/PDF output, this option requires at least version 3.0.25 of the siunitx LaTeX package. See the LaTeX preamble help section below for commands to insert in your LaTeX preamble.
`add_columns`	a data.frame (or tibble) with the same number of rows as your main table.
`add_rows`	a data.frame (or tibble) with the same number of columns as your main table. By default, rows are appended to the bottom of the table. You can define a "position" attribute of integers to set the row positions. See Examples section below.
`sparse_header`	TRUE or FALSE. TRUE eliminates column headers which have a unique label across all columns, except for the row immediately above the data. FALSE keeps all headers. The order in which terms are entered in the formula determines the order in which headers appear. For example, `x~mean*z` will print the `mean`-related header above the `z`-related header.'
`escape`	boolean TRUE escapes or substitutes LaTeX/HTML characters which could prevent the file from compiling/displaying. `TRUE` escapes all cells, captions, and notes. Users can have more fine-grained control by setting `escape=FALSE` and using an external command such as: `modelsummary(model, "latex") \|> tinytable::format_tt(tab, j=1:5, escape=TRUE)`
`...`	all other arguments are passed through to the table-making functions tinytable::tt, kableExtra::kbl, gt::gt, DT::datatable, etc. depending on the `output` argument. This allows users to pass arguments directly to `datasummary` in order to affect the behavior of other functions behind the scenes.

Details

Visit the 'modelsummary' website for more usage examples: https://modelsummary.com

The 'datasummary' function is a thin wrapper around the 'tabular' function from the 'tables' package. More details about table-making formulas can be found in the 'tables' package documentation: ?tables::tabular

Hierarchical or "nested" column labels are only available for these output formats: tinytable, kableExtra, gt, html, rtf, and LaTeX. When saving tables to other formats, nested labels will be combined to a "flat" header.

Version 2.0.0, kableExtra, and tinytable

Since version 2.0.0, modelsummary uses tinytable as its default table-drawing backend. Learn more at: https://vincentarelbundock.github.io/tinytable/",

Revert to kableExtra for one session:

options(modelsummary_factory_default = 'kableExtra') options(modelsummary_factory_latex = 'kableExtra') options(modelsummary_factory_html = 'kableExtra')

Global Options

The behavior of modelsummary can be modified by setting global options. For example:

options(modelsummary_model_labels = "roman")

The rest of this section describes each of the options above.

Model labels: default column names

These global option changes the style of the default column headers:

options(modelsummary_model_labels = "roman")
options(modelsummary_panel_labels = "roman")

The supported styles are: "model", "panel", "arabic", "letters", "roman", "(arabic)", "(letters)", "(roman)"

The panel-specific option is only used when shape="rbind"

Table-making packages

modelsummary supports 6 table-making packages: tinytable, kableExtra, gt, flextable, huxtable, and DT. Some of these packages have overlapping functionalities. To change the default backend used for a specific file format, you can use ' the options function:

options(modelsummary_factory_html = 'kableExtra') options(modelsummary_factory_word = 'huxtable') options(modelsummary_factory_png = 'gt') options(modelsummary_factory_latex = 'gt') options(modelsummary_factory_latex_tabular = 'kableExtra')

Table themes

Change the look of tables in an automated and replicable way, using the modelsummary theming functionality. See the vignette: https://modelsummary.com/articles/appearance.html

modelsummary_theme_gt
modelsummary_theme_kableExtra
modelsummary_theme_huxtable
modelsummary_theme_flextable
modelsummary_theme_dataframe

Model extraction functions

modelsummary can use two sets of packages to extract information from statistical models: the easystats family (performance and parameters) and broom. By default, it uses easystats first and then falls back on broom in case of failure. You can change the order of priorities or include goodness-of-fit extracted by both packages by setting:

options(modelsummary_get = "easystats")

options(modelsummary_get = "broom")

options(modelsummary_get = "all")

Formatting numeric entries

By default, LaTeX tables enclose all numeric entries in the ⁠\num{}⁠ command from the siunitx package. To prevent this behavior, or to enclose numbers in dollar signs (for LaTeX math mode), users can call:

options(modelsummary_format_numeric_latex = "plain")

options(modelsummary_format_numeric_latex = "mathmode")

A similar option can be used to display numerical entries using MathJax in HTML tables:

options(modelsummary_format_numeric_html = "mathjax")

LaTeX preamble

When creating LaTeX via the tinytable backend (default in version 2.0.0 and later), it is useful to include the following commands in the LaTeX preamble of your documents. Note that they are added automatically when compiling Rmarkdown or Quarto documents (except when the modelsummary() calls are cached).

\usepackage{tabularray}
\usepackage{float}
\usepackage{graphicx}
\usepackage[normalem]{ulem}
\UseTblrLibrary{booktabs}
\UseTblrLibrary{siunitx}
\newcommand{\tinytableTabularrayUnderline}[1]{\underline{#1}}
\newcommand{\tinytableTabularrayStrikeout}[1]{\sout{#1}}
\NewTableCommand{\tinytableDefineColor}[3]{\definecolor{#1}{#2}{#3}}

Examples

library(modelsummary)

# The left-hand side of the formula describes rows, and the right-hand side
# describes columns. This table uses the "mpg" variable as a row and the "mean"
# function as a column:

datasummary(mpg ~ mean, data = mtcars)

# This table uses the "mean" function as a row and the "mpg" variable as a column:

datasummary(mean ~ mpg, data = mtcars)

# Display several variables or functions of the data using the "+"
# concatenation operator. This table has 2 rows and 2 columns:

datasummary(hp + mpg ~ mean + sd, data = mtcars)

# Nest variables or statistics inside a "factor" variable using the "*" nesting
# operator. This table shows the mean of "hp" and "mpg" for each value of
# "cyl":

mtcars$cyl <- as.factor(mtcars$cyl)
datasummary(hp + mpg ~ cyl * mean, data = mtcars)

# If you don't want to convert your original data
# to factors, you can use the 'Factor()'
# function inside 'datasummary' to obtain an identical result:

datasummary(hp + mpg ~ Factor(cyl) * mean, data = mtcars)

# You can nest several variables or statistics inside a factor by using
# parentheses. This table shows the mean and the standard deviation for each
# subset of "cyl":

datasummary(hp + mpg ~ cyl * (mean + sd), data = mtcars)

# Summarize all numeric variables with 'All()'
datasummary(All(mtcars) ~ mean + sd, data = mtcars)

# Define custom summary statistics. Your custom function should accept a vector
# of numeric values and return a single numeric or string value:

minmax <- function(x) sprintf("[%.2f, %.2f]", min(x), max(x))
mean_na <- function(x) mean(x, na.rm = TRUE)

datasummary(hp + mpg ~ minmax + mean_na, data = mtcars)

# To handle missing values, you can pass arguments to your functions using
# '*Arguments()'

datasummary(hp + mpg ~ mean * Arguments(na.rm = TRUE), data = mtcars)

# For convenience, 'modelsummary' supplies several convenience functions
# with the argument `na.rm=TRUE` by default: Mean, Median, Min, Max, SD, Var,
# P0, P25, P50, P75, P100, NUnique, Histogram

#datasummary(hp + mpg ~ Mean + SD + Histogram, data = mtcars)

# These functions also accept a 'fmt' argument which allows you to
# round/format the results

datasummary(hp + mpg ~ Mean * Arguments(fmt = "%.3f") + SD * Arguments(fmt = "%.1f"), data = mtcars)

# Save your tables to a variety of output formats:
f <- hp + mpg ~ Mean + SD
#datasummary(f, data = mtcars, output = 'table.html')
#datasummary(f, data = mtcars, output = 'table.tex')
#datasummary(f, data = mtcars, output = 'table.md')
#datasummary(f, data = mtcars, output = 'table.docx')
#datasummary(f, data = mtcars, output = 'table.pptx')
#datasummary(f, data = mtcars, output = 'table.jpg')
#datasummary(f, data = mtcars, output = 'table.png')

# Display human-readable code
#datasummary(f, data = mtcars, output = 'html')
#datasummary(f, data = mtcars, output = 'markdown')
#datasummary(f, data = mtcars, output = 'latex')

# Return a table object to customize using a table-making package
#datasummary(f, data = mtcars, output = 'tinytable')
#datasummary(f, data = mtcars, output = 'gt')
#datasummary(f, data = mtcars, output = 'kableExtra')
#datasummary(f, data = mtcars, output = 'flextable')
#datasummary(f, data = mtcars, output = 'huxtable')

# add_rows
new_rows <- data.frame(a = 1:2, b = 2:3, c = 4:5)
attr(new_rows, 'position') <- c(1, 3)
datasummary(mpg + hp ~ mean + sd, data = mtcars, add_rows = new_rows)

References

Arel-Bundock V (2022). “modelsummary: Data and Model Summaries in R.” Journal of Statistical Software, 103(1), 1-23. doi:10.18637/jss.v103.i01.'

Balance table: Summary statistics for different subsets of the data (e.g., control and treatment groups)

Description

Creates balance tables with summary statistics for different subsets of the data (e.g., control and treatment groups). It can also be used to create summary tables for full data sets. See the Details and Examples sections below, and the vignettes on the modelsummary website:

https://modelsummary.com/
https://modelsummary.com/articles/datasummary.html

Usage

datasummary_balance(
  formula,
  data,
  output = "default",
  fmt = fmt_decimal(digits = 1, pdigits = 3),
  title = NULL,
  notes = NULL,
  align = NULL,
  stars = FALSE,
  add_columns = NULL,
  add_rows = NULL,
  dinm = TRUE,
  dinm_statistic = "std.error",
  escape = TRUE,
  ...
)
datasummary_balance(
  formula,
  data,
  output = "default",
  fmt = fmt_decimal(digits = 1, pdigits = 3),
  title = NULL,
  notes = NULL,
  align = NULL,
  stars = FALSE,
  add_columns = NULL,
  add_rows = NULL,
  dinm = TRUE,
  dinm_statistic = "std.error",
  escape = TRUE,
  ...
)

Arguments

`formula`	`~1`: show summary statistics for the full dataset one-sided formula: with the "condition" or "column" variable on the right-hand side. two-side formula: with the subset of variables to summarize on the left-hand side and the condition variable on the right-hand side.
`data`	A data.frame (or tibble). If this data includes columns called "blocks", "clusters", and/or "weights", the "estimatr" package will consider them when calculating the difference in means. If there is a `weights` column, the reported mean and standard errors will also be weighted.
`output`	filename or object type (character string) Supported filename extensions: .docx, .html, .tex, .md, .txt, .csv, .xlsx, .png, .jpg Supported object types: "default", "html", "markdown", "latex", "latex_tabular", "typst", "data.frame", "tinytable", "gt", "kableExtra", "huxtable", "flextable", "DT", "jupyter". The "modelsummary_list" value produces a lightweight object which can be saved and fed back to the `modelsummary` function. The "default" output format can be set to "tinytable", "kableExtra", "gt", "flextable", "huxtable", "DT", or "markdown" If the user does not choose a default value, the packages listed above are tried in sequence. Session-specific configuration: `options("modelsummary_factory_default" = "gt")` Persistent configuration: `config_modelsummary(output = "markdown")` Warning: Users should not supply a file name to the `output` argument if they intend to customize the table with external packages. See the 'Details' section. LaTeX compilation requires the `booktabs` and `siunitx` packages, but `siunitx` can be disabled or replaced with global options. See the 'Details' section.
`fmt`	how to format numeric values: integer, user-supplied function, or `modelsummary` function. Integer: Number of decimal digits User-supplied functions: Any function which accepts a numeric vector and returns a character vector of the same length. `modelsummary` functions: `fmt = fmt_significant(2)`: Two significant digits (at the term-level) `fmt = fmt_sprintf("%.3f")`: See `?sprintf` `fmt = fmt_identity()`: unformatted raw values
`title`	string. Cross-reference labels should be added with Quarto or Rmarkdown chunk options when applicable. When saving standalone LaTeX files, users can add a label such as `⁠\\label{tab:mytable}⁠` directly to the title string, while also specifying `escape=FALSE`.
`notes`	list or vector of notes to append to the bottom of the table.
`align`	A string with a number of characters equal to the number of columns in the table (e.g., `align = "lcc"`). Valid characters: l, c, r, d. "l": left-aligned column "c": centered column "r": right-aligned column "d": dot-aligned column. For LaTeX/PDF output, this option requires at least version 3.0.25 of the siunitx LaTeX package. See the LaTeX preamble help section below for commands to insert in your LaTeX preamble.
`stars`	to indicate statistical significance FALSE (default): no significance stars. TRUE: `c("+" = .1, "" = .05, "" = .01, "*" = 0.001)` Named numeric vector for custom stars such as `c('' = .1, '+' = .05)` Note: a legend will not be inserted at the bottom of the table when the `estimate` or `statistic` arguments use "glue strings" with `{stars}`.
`add_columns`	a data.frame (or tibble) with the same number of rows as your main table.
`add_rows`	a data.frame (or tibble) with the same number of columns as your main table. By default, rows are appended to the bottom of the table. You can define a "position" attribute of integers to set the row positions. See Examples section below.
`dinm`	TRUE calculates a difference in means with uncertainty estimates. This option is only available if the `estimatr` package is installed. If `data` includes columns named "blocks", "clusters", or "weights", this information will be taken into account automatically by `estimatr::difference_in_means`.
`dinm_statistic`	string: "std.error" or "p.value"
`escape`	boolean TRUE escapes or substitutes LaTeX/HTML characters which could prevent the file from compiling/displaying. `TRUE` escapes all cells, captions, and notes. Users can have more fine-grained control by setting `escape=FALSE` and using an external command such as: `modelsummary(model, "latex") \|> tinytable::format_tt(tab, j=1:5, escape=TRUE)`
`...`	all other arguments are passed through to the table-making functions tinytable::tt, kableExtra::kbl, gt::gt, DT::datatable, etc. depending on the `output` argument. This allows users to pass arguments directly to `datasummary` in order to affect the behavior of other functions behind the scenes.

Version 2.0.0, kableExtra, and tinytable

Since version 2.0.0, modelsummary uses tinytable as its default table-drawing backend. Learn more at: https://vincentarelbundock.github.io/tinytable/",

Revert to kableExtra for one session:

options(modelsummary_factory_default = 'kableExtra') options(modelsummary_factory_latex = 'kableExtra') options(modelsummary_factory_html = 'kableExtra')

Global Options

The behavior of modelsummary can be modified by setting global options. For example:

options(modelsummary_model_labels = "roman")

The rest of this section describes each of the options above.

Model labels: default column names

These global option changes the style of the default column headers:

options(modelsummary_model_labels = "roman")
options(modelsummary_panel_labels = "roman")

The supported styles are: "model", "panel", "arabic", "letters", "roman", "(arabic)", "(letters)", "(roman)"

The panel-specific option is only used when shape="rbind"

Table-making packages

Table themes

Change the look of tables in an automated and replicable way, using the modelsummary theming functionality. See the vignette: https://modelsummary.com/articles/appearance.html

modelsummary_theme_gt
modelsummary_theme_kableExtra
modelsummary_theme_huxtable
modelsummary_theme_flextable
modelsummary_theme_dataframe

Model extraction functions

options(modelsummary_get = "easystats")

options(modelsummary_get = "broom")

options(modelsummary_get = "all")

Formatting numeric entries

options(modelsummary_format_numeric_latex = "plain")

options(modelsummary_format_numeric_latex = "mathmode")

A similar option can be used to display numerical entries using MathJax in HTML tables:

options(modelsummary_format_numeric_html = "mathjax")

LaTeX preamble

\usepackage{tabularray}
\usepackage{float}
\usepackage{graphicx}
\usepackage[normalem]{ulem}
\UseTblrLibrary{booktabs}
\UseTblrLibrary{siunitx}
\newcommand{\tinytableTabularrayUnderline}[1]{\underline{#1}}
\newcommand{\tinytableTabularrayStrikeout}[1]{\sout{#1}}
\NewTableCommand{\tinytableDefineColor}[3]{\definecolor{#1}{#2}{#3}}

Examples

library(modelsummary)
datasummary_balance(~am, mtcars)

References

Arel-Bundock V (2022). “modelsummary: Data and Model Summaries in R.” Journal of Statistical Software, 103(1), 1-23. doi:10.18637/jss.v103.i01.'

Generate a correlation table for all numeric variables in your dataset.

Description

The names of the variables displayed in the correlation table are the names of the columns in the data. You can rename those columns (with or without spaces) to produce a table of human-readable variables. See the Details and Examples sections below, and the vignettes on the modelsummary website:

https://modelsummary.com/
https://modelsummary.com/articles/datasummary.html

Usage

datasummary_correlation(
  data,
  output = "default",
  method = "pearson",
  fmt = 2,
  align = NULL,
  add_rows = NULL,
  add_columns = NULL,
  title = NULL,
  notes = NULL,
  escape = TRUE,
  stars = FALSE,
  ...
)
datasummary_correlation(
  data,
  output = "default",
  method = "pearson",
  fmt = 2,
  align = NULL,
  add_rows = NULL,
  add_columns = NULL,
  title = NULL,
  notes = NULL,
  escape = TRUE,
  stars = FALSE,
  ...
)

Arguments

`data`	A data.frame (or tibble)
`output`	filename or object type (character string) Supported filename extensions: .docx, .html, .tex, .md, .txt, .csv, .xlsx, .png, .jpg Supported object types: "default", "html", "markdown", "latex", "latex_tabular", "typst", "data.frame", "tinytable", "gt", "kableExtra", "huxtable", "flextable", "DT", "jupyter". The "modelsummary_list" value produces a lightweight object which can be saved and fed back to the `modelsummary` function. The "default" output format can be set to "tinytable", "kableExtra", "gt", "flextable", "huxtable", "DT", or "markdown" If the user does not choose a default value, the packages listed above are tried in sequence. Session-specific configuration: `options("modelsummary_factory_default" = "gt")` Persistent configuration: `config_modelsummary(output = "markdown")` Warning: Users should not supply a file name to the `output` argument if they intend to customize the table with external packages. See the 'Details' section. LaTeX compilation requires the `booktabs` and `siunitx` packages, but `siunitx` can be disabled or replaced with global options. See the 'Details' section.
`method`	character or function character: "pearson", "kendall", "spearman", or "pearspear" (Pearson correlations above and Spearman correlations below the diagonal) function: takes a data.frame with numeric columns and returns a square matrix or data.frame with unique row.names and colnames corresponding to variable names. Note that the `datasummary_correlation_format` can often be useful for formatting the output of custom correlation functions.
`fmt`	how to format numeric values: integer, user-supplied function, or `modelsummary` function. Integer: Number of decimal digits User-supplied functions: Any function which accepts a numeric vector and returns a character vector of the same length. `modelsummary` functions: `fmt = fmt_significant(2)`: Two significant digits (at the term-level) `fmt = fmt_sprintf("%.3f")`: See `?sprintf` `fmt = fmt_identity()`: unformatted raw values
`align`	A string with a number of characters equal to the number of columns in the table (e.g., `align = "lcc"`). Valid characters: l, c, r, d. "l": left-aligned column "c": centered column "r": right-aligned column "d": dot-aligned column. For LaTeX/PDF output, this option requires at least version 3.0.25 of the siunitx LaTeX package. See the LaTeX preamble help section below for commands to insert in your LaTeX preamble.
`add_rows`	a data.frame (or tibble) with the same number of columns as your main table. By default, rows are appended to the bottom of the table. You can define a "position" attribute of integers to set the row positions. See Examples section below.
`add_columns`	a data.frame (or tibble) with the same number of rows as your main table.
`title`	string. Cross-reference labels should be added with Quarto or Rmarkdown chunk options when applicable. When saving standalone LaTeX files, users can add a label such as `⁠\\label{tab:mytable}⁠` directly to the title string, while also specifying `escape=FALSE`.
`notes`	list or vector of notes to append to the bottom of the table.
`escape`	boolean TRUE escapes or substitutes LaTeX/HTML characters which could prevent the file from compiling/displaying. `TRUE` escapes all cells, captions, and notes. Users can have more fine-grained control by setting `escape=FALSE` and using an external command such as: `modelsummary(model, "latex") \|> tinytable::format_tt(tab, j=1:5, escape=TRUE)`
`stars`	to indicate statistical significance FALSE (default): no significance stars. TRUE: `c("+" = .1, "" = .05, "" = .01, "*" = 0.001)` Named numeric vector for custom stars such as `c('' = .1, '+' = .05)` Note: a legend will not be inserted at the bottom of the table when the `estimate` or `statistic` arguments use "glue strings" with `{stars}`.
`...`	other parameters are passed through to the table-making packages.

Version 2.0.0, kableExtra, and tinytable

Since version 2.0.0, modelsummary uses tinytable as its default table-drawing backend. Learn more at: https://vincentarelbundock.github.io/tinytable/",

Revert to kableExtra for one session:

options(modelsummary_factory_default = 'kableExtra') options(modelsummary_factory_latex = 'kableExtra') options(modelsummary_factory_html = 'kableExtra')

Global Options

The behavior of modelsummary can be modified by setting global options. For example:

options(modelsummary_model_labels = "roman")

The rest of this section describes each of the options above.

Model labels: default column names

These global option changes the style of the default column headers:

options(modelsummary_model_labels = "roman")
options(modelsummary_panel_labels = "roman")

The supported styles are: "model", "panel", "arabic", "letters", "roman", "(arabic)", "(letters)", "(roman)"

The panel-specific option is only used when shape="rbind"

Table-making packages

Table themes

Change the look of tables in an automated and replicable way, using the modelsummary theming functionality. See the vignette: https://modelsummary.com/articles/appearance.html

modelsummary_theme_gt
modelsummary_theme_kableExtra
modelsummary_theme_huxtable
modelsummary_theme_flextable
modelsummary_theme_dataframe

Model extraction functions

options(modelsummary_get = "easystats")

options(modelsummary_get = "broom")

options(modelsummary_get = "all")

Formatting numeric entries

options(modelsummary_format_numeric_latex = "plain")

options(modelsummary_format_numeric_latex = "mathmode")

A similar option can be used to display numerical entries using MathJax in HTML tables:

options(modelsummary_format_numeric_html = "mathjax")

LaTeX preamble

\usepackage{tabularray}
\usepackage{float}
\usepackage{graphicx}
\usepackage[normalem]{ulem}
\UseTblrLibrary{booktabs}
\UseTblrLibrary{siunitx}
\newcommand{\tinytableTabularrayUnderline}[1]{\underline{#1}}
\newcommand{\tinytableTabularrayStrikeout}[1]{\sout{#1}}
\NewTableCommand{\tinytableDefineColor}[3]{\definecolor{#1}{#2}{#3}}

Examples

library(modelsummary)

# clean variable names (base R)
dat <- mtcars[, c("mpg", "hp")]
colnames(dat) <- c("Miles / Gallon", "Horse Power")
datasummary_correlation(dat)

# clean variable names (tidyverse)
library(tidyverse)
dat <- mtcars %>%
  select(`Miles / Gallon` = mpg,
         `Horse Power` = hp)
datasummary_correlation(dat)

# `correlation` package objects
if (requireNamespace("correlation", quietly = TRUE)) {
  co <- correlation::correlation(mtcars[, 1:4])
  datasummary_correlation(co)

  # add stars to easycorrelation objects
  datasummary_correlation(co, stars = TRUE)
}

# alternative methods
datasummary_correlation(dat, method = "pearspear")

# custom function
cor_fun <- function(x) cor(x, method = "kendall")
datasummary_correlation(dat, method = cor_fun)

# rename columns alphabetically and include a footnote for reference
note <- sprintf("(%s) %s", letters[1:ncol(dat)], colnames(dat))
note <- paste(note, collapse = "; ")

colnames(dat) <- sprintf("(%s)", letters[1:ncol(dat)])

datasummary_correlation(dat, notes = note)

# `datasummary_correlation_format`: custom function with formatting
dat <- mtcars[, c("mpg", "hp", "disp")]

cor_fun <- function(x) {
  out <- cor(x, method = "kendall")
  datasummary_correlation_format(
    out,
    fmt = 2,
    upper_triangle = "x",
    diagonal = ".")
}

datasummary_correlation(dat, method = cor_fun)

# use kableExtra and psych to color significant cells
library(psych)
library(kableExtra)

dat <- mtcars[, c("vs", "hp", "gear")]

cor_fun <- function(dat) {
  # compute correlations and format them
  correlations <- data.frame(cor(dat))
  correlations <- datasummary_correlation_format(correlations, fmt = 2)

  # calculate pvalues using the `psych` package
  pvalues <- psych::corr.test(dat)$p

  # use `kableExtra::cell_spec` to color significant cells
  for (i in 1:nrow(correlations)) {
    for (j in 1:ncol(correlations)) {
      if (pvalues[i, j] < 0.05 && i != j) {
        correlations[i, j] <- cell_spec(correlations[i, j], background = "pink")
      }
    }
  }
  return(correlations)
}

# The `escape=FALSE` is important here!
datasummary_correlation(dat, method = cor_fun, escape = FALSE)

References

Arel-Bundock V (2022). “modelsummary: Data and Model Summaries in R.” Journal of Statistical Software, 103(1), 1-23. doi:10.18637/jss.v103.i01.'

Format the content of a correlation table

Description

Mostly for internal use, but can be useful when users supply a function to the method argument of datasummary_correlation.

Usage

datasummary_correlation_format(
  x,
  fmt,
  leading_zero = FALSE,
  diagonal = NULL,
  upper_triangle = NULL,
  stars = FALSE
)
datasummary_correlation_format(
  x,
  fmt,
  leading_zero = FALSE,
  diagonal = NULL,
  upper_triangle = NULL,
  stars = FALSE
)

Arguments

`x`	square numeric matrix
`fmt`	how to format numeric values: integer, user-supplied function, or `modelsummary` function. Integer: Number of decimal digits User-supplied functions: Any function which accepts a numeric vector and returns a character vector of the same length. `modelsummary` functions: `fmt = fmt_significant(2)`: Two significant digits (at the term-level) `fmt = fmt_sprintf("%.3f")`: See `?sprintf` `fmt = fmt_identity()`: unformatted raw values
`leading_zero`	boolean. If `FALSE`, leading zeros are removed
`diagonal`	character or NULL. If character, all elements of the diagonal are replaced by the same character (e.g., "1").
`upper_triangle`	character or NULL. If character, all elements of the upper triangle are replaced by the same character (e.g., "" or ".").
`stars`	to indicate statistical significance FALSE (default): no significance stars. TRUE: `c("+" = .1, "" = .05, "" = .01, "*" = 0.001)` Named numeric vector for custom stars such as `c('' = .1, '+' = .05)` Note: a legend will not be inserted at the bottom of the table when the `estimate` or `statistic` arguments use "glue strings" with `{stars}`.

Examples

library(modelsummary)

dat <- mtcars[, c("mpg", "hp", "disp")]

cor_fun <- function(x) {
  out <- cor(x, method = "kendall")
  datasummary_correlation_format(
    out,
    fmt = 2,
    upper_triangle = "x",
    diagonal = ".")
}

datasummary_correlation(dat, method = cor_fun)
library(modelsummary)

dat <- mtcars[, c("mpg", "hp", "disp")]

cor_fun <- function(x) {
  out <- cor(x, method = "kendall")
  datasummary_correlation_format(
    out,
    fmt = 2,
    upper_triangle = "x",
    diagonal = ".")
}

datasummary_correlation(dat, method = cor_fun)

Cross tabulations for categorical variables

Description

Convenience function to tabulate counts, cell percentages, and row/column percentages for categorical variables. See the Details section for a description of the internal design. For more complex cross tabulations, use datasummary directly. See the Details and Examples sections below, and the vignettes on the modelsummary website:

https://modelsummary.com/
https://modelsummary.com/articles/datasummary.html

Usage

datasummary_crosstab(
  formula,
  statistic = 1 ~ 1 + N + Percent("row"),
  data,
  output = "default",
  fmt = 1,
  title = NULL,
  notes = NULL,
  align = NULL,
  add_columns = NULL,
  add_rows = NULL,
  sparse_header = TRUE,
  escape = TRUE,
  ...
)
datasummary_crosstab(
  formula,
  statistic = 1 ~ 1 + N + Percent("row"),
  data,
  output = "default",
  fmt = 1,
  title = NULL,
  notes = NULL,
  align = NULL,
  add_columns = NULL,
  add_rows = NULL,
  sparse_header = TRUE,
  escape = TRUE,
  ...
)

Arguments

`formula`	A two-sided formula to describe the table: rows ~ columns, where rows and columns are variables in the data. Rows and columns may contain interactions, e.g., `var1 * var2 ~ var3`.
`statistic`	A formula of the form `1 ~ 1 + N + Percent("row")`. The left-hand side may only be empty or contain a `1` to include row totals. The right-hand side may contain: `1` for column totals, `N` for counts, `Percent()` for cell percentages, `Percent("row")` for row percentages, `Percent("col")` for column percentages.
`data`	A data.frame (or tibble)
`output`	filename or object type (character string) Supported filename extensions: .docx, .html, .tex, .md, .txt, .csv, .xlsx, .png, .jpg Supported object types: "default", "html", "markdown", "latex", "latex_tabular", "typst", "data.frame", "tinytable", "gt", "kableExtra", "huxtable", "flextable", "DT", "jupyter". The "modelsummary_list" value produces a lightweight object which can be saved and fed back to the `modelsummary` function. The "default" output format can be set to "tinytable", "kableExtra", "gt", "flextable", "huxtable", "DT", or "markdown" If the user does not choose a default value, the packages listed above are tried in sequence. Session-specific configuration: `options("modelsummary_factory_default" = "gt")` Persistent configuration: `config_modelsummary(output = "markdown")` Warning: Users should not supply a file name to the `output` argument if they intend to customize the table with external packages. See the 'Details' section. LaTeX compilation requires the `booktabs` and `siunitx` packages, but `siunitx` can be disabled or replaced with global options. See the 'Details' section.
`fmt`	how to format numeric values: integer, user-supplied function, or `modelsummary` function. Integer: Number of decimal digits User-supplied functions: Any function which accepts a numeric vector and returns a character vector of the same length. `modelsummary` functions: `fmt = fmt_significant(2)`: Two significant digits (at the term-level) `fmt = fmt_sprintf("%.3f")`: See `?sprintf` `fmt = fmt_identity()`: unformatted raw values
`title`	string. Cross-reference labels should be added with Quarto or Rmarkdown chunk options when applicable. When saving standalone LaTeX files, users can add a label such as `⁠\\label{tab:mytable}⁠` directly to the title string, while also specifying `escape=FALSE`.
`notes`	list or vector of notes to append to the bottom of the table.
`align`	A string with a number of characters equal to the number of columns in the table (e.g., `align = "lcc"`). Valid characters: l, c, r, d. "l": left-aligned column "c": centered column "r": right-aligned column "d": dot-aligned column. For LaTeX/PDF output, this option requires at least version 3.0.25 of the siunitx LaTeX package. See the LaTeX preamble help section below for commands to insert in your LaTeX preamble.
`add_columns`	a data.frame (or tibble) with the same number of rows as your main table.
`add_rows`	a data.frame (or tibble) with the same number of columns as your main table. By default, rows are appended to the bottom of the table. You can define a "position" attribute of integers to set the row positions. See Examples section below.
`sparse_header`	TRUE or FALSE. TRUE eliminates column headers which have a unique label across all columns, except for the row immediately above the data. FALSE keeps all headers. The order in which terms are entered in the formula determines the order in which headers appear. For example, `x~mean*z` will print the `mean`-related header above the `z`-related header.'
`escape`	boolean TRUE escapes or substitutes LaTeX/HTML characters which could prevent the file from compiling/displaying. `TRUE` escapes all cells, captions, and notes. Users can have more fine-grained control by setting `escape=FALSE` and using an external command such as: `modelsummary(model, "latex") \|> tinytable::format_tt(tab, j=1:5, escape=TRUE)`
`...`	all other arguments are passed through to the table-making functions tinytable::tt, kableExtra::kbl, gt::gt, DT::datatable, etc. depending on the `output` argument. This allows users to pass arguments directly to `datasummary` in order to affect the behavior of other functions behind the scenes.

Details

datasummary_crosstab is a wrapper around the datasummary function. This wrapper works by creating a customized formula and by feeding it to datasummary. The customized formula comes in two parts.

First, we take a two-sided formula supplied by the formula argument. All variables of that formula are wrapped in a Factor() call to ensure that the variables are treated as categorical.

Second, the statistic argument gives a two-sided formula which specifies the statistics to include in the table. datasummary_crosstab modifies this formula automatically to include "clean" labels.

Finally, the formula and statistic formulas are combined into a single formula which is fed directly to the datasummary function to produce the table.

Variables in formula are automatically wrapped in Factor().

Version 2.0.0, kableExtra, and tinytable

Since version 2.0.0, modelsummary uses tinytable as its default table-drawing backend. Learn more at: https://vincentarelbundock.github.io/tinytable/",

Revert to kableExtra for one session:

options(modelsummary_factory_default = 'kableExtra') options(modelsummary_factory_latex = 'kableExtra') options(modelsummary_factory_html = 'kableExtra')

Global Options

The behavior of modelsummary can be modified by setting global options. For example:

options(modelsummary_model_labels = "roman")

The rest of this section describes each of the options above.

Model labels: default column names

These global option changes the style of the default column headers:

options(modelsummary_model_labels = "roman")
options(modelsummary_panel_labels = "roman")

The supported styles are: "model", "panel", "arabic", "letters", "roman", "(arabic)", "(letters)", "(roman)"

The panel-specific option is only used when shape="rbind"

Table-making packages

Table themes

Change the look of tables in an automated and replicable way, using the modelsummary theming functionality. See the vignette: https://modelsummary.com/articles/appearance.html

modelsummary_theme_gt
modelsummary_theme_kableExtra
modelsummary_theme_huxtable
modelsummary_theme_flextable
modelsummary_theme_dataframe

Model extraction functions

options(modelsummary_get = "easystats")

options(modelsummary_get = "broom")

options(modelsummary_get = "all")

Formatting numeric entries

options(modelsummary_format_numeric_latex = "plain")

options(modelsummary_format_numeric_latex = "mathmode")

A similar option can be used to display numerical entries using MathJax in HTML tables:

options(modelsummary_format_numeric_html = "mathjax")

LaTeX preamble

\usepackage{tabularray}
\usepackage{float}
\usepackage{graphicx}
\usepackage[normalem]{ulem}
\UseTblrLibrary{booktabs}
\UseTblrLibrary{siunitx}
\newcommand{\tinytableTabularrayUnderline}[1]{\underline{#1}}
\newcommand{\tinytableTabularrayStrikeout}[1]{\sout{#1}}
\NewTableCommand{\tinytableDefineColor}[3]{\definecolor{#1}{#2}{#3}}

Examples

library(modelsummary)

# crosstab of two variables, showing counts, row percentages, and row/column totals
datasummary_crosstab(cyl ~ gear, data = mtcars)

# crosstab of two variables, showing counts only and no totals
datasummary_crosstab(cyl ~ gear, statistic = ~ N, data = mtcars)

# crosstab of three variables
  datasummary_crosstab(am * cyl ~ gear, data = mtcars)

# crosstab with two variables and column percentages
datasummary_crosstab(am ~ gear, statistic = ~ Percent("col"), data = mtcars)

References

Arel-Bundock V (2022). “modelsummary: Data and Model Summaries in R.” Journal of Statistical Software, 103(1), 1-23. doi:10.18637/jss.v103.i01.'

Draw a table from a data.frame

Description

Draw a table from a data.frame

Usage

datasummary_df(
  data,
  output = "default",
  fmt = 2,
  align = NULL,
  hrule = NULL,
  title = NULL,
  notes = NULL,
  add_rows = NULL,
  add_columns = NULL,
  escape = TRUE,
  ...
)
datasummary_df(
  data,
  output = "default",
  fmt = 2,
  align = NULL,
  hrule = NULL,
  title = NULL,
  notes = NULL,
  add_rows = NULL,
  add_columns = NULL,
  escape = TRUE,
  ...
)

Arguments

`data`	A data.frame (or tibble)
`output`	filename or object type (character string) Supported filename extensions: .docx, .html, .tex, .md, .txt, .csv, .xlsx, .png, .jpg Supported object types: "default", "html", "markdown", "latex", "latex_tabular", "typst", "data.frame", "tinytable", "gt", "kableExtra", "huxtable", "flextable", "DT", "jupyter". The "modelsummary_list" value produces a lightweight object which can be saved and fed back to the `modelsummary` function. The "default" output format can be set to "tinytable", "kableExtra", "gt", "flextable", "huxtable", "DT", or "markdown" If the user does not choose a default value, the packages listed above are tried in sequence. Session-specific configuration: `options("modelsummary_factory_default" = "gt")` Persistent configuration: `config_modelsummary(output = "markdown")` Warning: Users should not supply a file name to the `output` argument if they intend to customize the table with external packages. See the 'Details' section. LaTeX compilation requires the `booktabs` and `siunitx` packages, but `siunitx` can be disabled or replaced with global options. See the 'Details' section.
`fmt`	how to format numeric values: integer, user-supplied function, or `modelsummary` function. Integer: Number of decimal digits User-supplied functions: Any function which accepts a numeric vector and returns a character vector of the same length. `modelsummary` functions: `fmt = fmt_significant(2)`: Two significant digits (at the term-level) `fmt = fmt_sprintf("%.3f")`: See `?sprintf` `fmt = fmt_identity()`: unformatted raw values
`align`	A string with a number of characters equal to the number of columns in the table (e.g., `align = "lcc"`). Valid characters: l, c, r, d. "l": left-aligned column "c": centered column "r": right-aligned column "d": dot-aligned column. For LaTeX/PDF output, this option requires at least version 3.0.25 of the siunitx LaTeX package. See the LaTeX preamble help section below for commands to insert in your LaTeX preamble.
`hrule`	position of horizontal rules (integer vector)
`title`	string. Cross-reference labels should be added with Quarto or Rmarkdown chunk options when applicable. When saving standalone LaTeX files, users can add a label such as `⁠\\label{tab:mytable}⁠` directly to the title string, while also specifying `escape=FALSE`.
`notes`	list or vector of notes to append to the bottom of the table.
`add_rows`	a data.frame (or tibble) with the same number of columns as your main table. By default, rows are appended to the bottom of the table. You can define a "position" attribute of integers to set the row positions. See Examples section below.
`add_columns`	a data.frame (or tibble) with the same number of rows as your main table.
`escape`	boolean TRUE escapes or substitutes LaTeX/HTML characters which could prevent the file from compiling/displaying. `TRUE` escapes all cells, captions, and notes. Users can have more fine-grained control by setting `escape=FALSE` and using an external command such as: `modelsummary(model, "latex") \|> tinytable::format_tt(tab, j=1:5, escape=TRUE)`
`...`	all other arguments are passed through to the table-making functions tinytable::tt, kableExtra::kbl, gt::gt, DT::datatable, etc. depending on the `output` argument. This allows users to pass arguments directly to `datasummary` in order to affect the behavior of other functions behind the scenes.

Version 2.0.0, kableExtra, and tinytable

Since version 2.0.0, modelsummary uses tinytable as its default table-drawing backend. Learn more at: https://vincentarelbundock.github.io/tinytable/",

Revert to kableExtra for one session:

options(modelsummary_factory_default = 'kableExtra') options(modelsummary_factory_latex = 'kableExtra') options(modelsummary_factory_html = 'kableExtra')

References

Arel-Bundock V (2022). “modelsummary: Data and Model Summaries in R.” Journal of Statistical Software, 103(1), 1-23. doi:10.18637/jss.v103.i01.'

Quick overview of numeric or categorical variables

Description

This function was inspired by the excellent skimr package for R. See the Details and Examples sections below, and the vignettes on the modelsummary website:

https://modelsummary.com/
https://modelsummary.com/articles/datasummary.html

Usage

datasummary_skim(
  data,
  output = "default",
  type = "all",
  fmt = 1,
  title = NULL,
  notes = NULL,
  align = NULL,
  escape = TRUE,
  by = NULL,
  fun_numeric = list(Unique = NUnique, `Missing Pct.` = PercentMissing, Mean = Mean, SD =
    SD, Min = Min, Median = Median, Max = Max, Histogram = function(x) ""),
  ...
)
datasummary_skim(
  data,
  output = "default",
  type = "all",
  fmt = 1,
  title = NULL,
  notes = NULL,
  align = NULL,
  escape = TRUE,
  by = NULL,
  fun_numeric = list(Unique = NUnique, `Missing Pct.` = PercentMissing, Mean = Mean, SD =
    SD, Min = Min, Median = Median, Max = Max, Histogram = function(x) ""),
  ...
)

Arguments

`data`	A data.frame (or tibble)
`output`	filename or object type (character string) Supported filename extensions: .docx, .html, .tex, .md, .txt, .csv, .xlsx, .png, .jpg Supported object types: "default", "html", "markdown", "latex", "latex_tabular", "typst", "data.frame", "tinytable", "gt", "kableExtra", "huxtable", "flextable", "DT", "jupyter". The "modelsummary_list" value produces a lightweight object which can be saved and fed back to the `modelsummary` function. The "default" output format can be set to "tinytable", "kableExtra", "gt", "flextable", "huxtable", "DT", or "markdown" If the user does not choose a default value, the packages listed above are tried in sequence. Session-specific configuration: `options("modelsummary_factory_default" = "gt")` Persistent configuration: `config_modelsummary(output = "markdown")` Warning: Users should not supply a file name to the `output` argument if they intend to customize the table with external packages. See the 'Details' section. LaTeX compilation requires the `booktabs` and `siunitx` packages, but `siunitx` can be disabled or replaced with global options. See the 'Details' section.
`type`	String. Variables to summarize: "all", "numeric", "categorical", "dataset"
`fmt`	how to format numeric values: integer, user-supplied function, or `modelsummary` function. Integer: Number of decimal digits User-supplied functions: Any function which accepts a numeric vector and returns a character vector of the same length. `modelsummary` functions: `fmt = fmt_significant(2)`: Two significant digits (at the term-level) `fmt = fmt_sprintf("%.3f")`: See `?sprintf` `fmt = fmt_identity()`: unformatted raw values
`title`	string. Cross-reference labels should be added with Quarto or Rmarkdown chunk options when applicable. When saving standalone LaTeX files, users can add a label such as `⁠\\label{tab:mytable}⁠` directly to the title string, while also specifying `escape=FALSE`.
`notes`	list or vector of notes to append to the bottom of the table.
`align`	A string with a number of characters equal to the number of columns in the table (e.g., `align = "lcc"`). Valid characters: l, c, r, d. "l": left-aligned column "c": centered column "r": right-aligned column "d": dot-aligned column. For LaTeX/PDF output, this option requires at least version 3.0.25 of the siunitx LaTeX package. See the LaTeX preamble help section below for commands to insert in your LaTeX preamble.
`escape`	boolean TRUE escapes or substitutes LaTeX/HTML characters which could prevent the file from compiling/displaying. `TRUE` escapes all cells, captions, and notes. Users can have more fine-grained control by setting `escape=FALSE` and using an external command such as: `modelsummary(model, "latex") \|> tinytable::format_tt(tab, j=1:5, escape=TRUE)`
`by`	Character vector of grouping variables to compute statistics over.
`fun_numeric`	Named list of funtions to apply to each numeric column of `data`. If `fun_numeric` includes "Histogram" or "Density", inline plots are inserted. This argument is only used when `type="numeric"` or `"all"`.
`...`	all other arguments are passed through to the table-making functions tinytable::tt, kableExtra::kbl, gt::gt, DT::datatable, etc. depending on the `output` argument. This allows users to pass arguments directly to `datasummary` in order to affect the behavior of other functions behind the scenes.

Version 2.0.0, kableExtra, and tinytable

Since version 2.0.0, modelsummary uses tinytable as its default table-drawing backend. Learn more at: https://vincentarelbundock.github.io/tinytable/",

Revert to kableExtra for one session:

options(modelsummary_factory_default = 'kableExtra') options(modelsummary_factory_latex = 'kableExtra') options(modelsummary_factory_html = 'kableExtra')

Global Options

The behavior of modelsummary can be modified by setting global options. For example:

options(modelsummary_model_labels = "roman")

The rest of this section describes each of the options above.

Model labels: default column names

These global option changes the style of the default column headers:

options(modelsummary_model_labels = "roman")
options(modelsummary_panel_labels = "roman")

The supported styles are: "model", "panel", "arabic", "letters", "roman", "(arabic)", "(letters)", "(roman)"

The panel-specific option is only used when shape="rbind"

Table-making packages

Table themes

Change the look of tables in an automated and replicable way, using the modelsummary theming functionality. See the vignette: https://modelsummary.com/articles/appearance.html

modelsummary_theme_gt
modelsummary_theme_kableExtra
modelsummary_theme_huxtable
modelsummary_theme_flextable
modelsummary_theme_dataframe

Model extraction functions

options(modelsummary_get = "easystats")

options(modelsummary_get = "broom")

options(modelsummary_get = "all")

Formatting numeric entries

options(modelsummary_format_numeric_latex = "plain")

options(modelsummary_format_numeric_latex = "mathmode")

A similar option can be used to display numerical entries using MathJax in HTML tables:

options(modelsummary_format_numeric_html = "mathjax")

LaTeX preamble

\usepackage{tabularray}
\usepackage{float}
\usepackage{graphicx}
\usepackage[normalem]{ulem}
\UseTblrLibrary{booktabs}
\UseTblrLibrary{siunitx}
\newcommand{\tinytableTabularrayUnderline}[1]{\underline{#1}}
\newcommand{\tinytableTabularrayStrikeout}[1]{\sout{#1}}
\NewTableCommand{\tinytableDefineColor}[3]{\definecolor{#1}{#2}{#3}}

References

Arel-Bundock V (2022). “modelsummary: Data and Model Summaries in R.” Journal of Statistical Software, 103(1), 1-23. doi:10.18637/jss.v103.i01.'

Examples


dat <- mtcars
dat$vs <- as.logical(dat$vs)
dat$cyl <- as.factor(dat$cyl)
datasummary_skim(dat)
datasummary_skim(dat, type = "categorical")

dat <- mtcars
dat$vs <- as.logical(dat$vs)
dat$cyl <- as.factor(dat$cyl)
datasummary_skim(dat)
datasummary_skim(dat, type = "categorical")

Title models with their dependent variables

Description

A convenience function for use with a regression model or list of regression models. Returns a named list of models, where the names are the models' respective dependent variables. Pass your list of models to dvnames before sending to modelsummary to automatically get dependent variable-titled columns.

Usage

dvnames(models, number = FALSE, strip = FALSE, fill = "Model")
dvnames(models, number = FALSE, strip = FALSE, fill = "Model")

Arguments

`models`	A regression model or list of regression models
`number`	Should the models be numbered (1), (2), etc., in addition to their dependent variable names?
`strip`	boolean FALSE returns the dependent variable names as they appear in the model. TRUE returns the dependent variable names as they appear in the data, without transformations.
`fill`	If `insight::find_response()` cannot find a response, the column title to use in its place. Set to `' '` to leave blank.

Examples


m1 <- lm(mpg ~ hp, data = mtcars)
m2 <- lm(mpg ~ hp + wt, data = mtcars)

# Without dvnames, column names are (1) and (2)
modelsummary(list(m1, m2))

# With dvnames, they are "mpg" and "mpg"
modelsummary(dvnames(list(m1,m2)))

m1 <- lm(mpg ~ hp, data = mtcars)
m2 <- lm(mpg ~ hp + wt, data = mtcars)

# Without dvnames, column names are (1) and (2)
modelsummary(list(m1, m2))

# With dvnames, they are "mpg" and "mpg"
modelsummary(dvnames(list(m1,m2)))

Rounding with decimal digits in the `fmt` argument

Description

Rounding with decimal digits in the fmt argument

Usage

fmt_decimal(digits = 3, pdigits = NULL, ...)
fmt_decimal(digits = 3, pdigits = NULL, ...)

Arguments

`digits`	Number of decimal digits to keep, including trailing zeros.
`pdigits`	Number of decimal digits to keep for p values. If `NULL`, the value of `digits` is used.
`...`	Additional arguments are passed to the `format()` function (e.g., `big.marks`, `scientific`). See `?format`

Rounding with number of digits determined by an equivalence test

Description

This function implements the suggestions of Astier & Wolak for the number of decimal digits to keep for coefficient estimates. The other statistics are rounded by fmt_significant().

Usage

fmt_equivalence(conf_level = 0.95, digits = 3, pdigits = NULL, ...)
fmt_equivalence(conf_level = 0.95, digits = 3, pdigits = NULL, ...)

Arguments

`conf_level`	Confidence level to use for the equivalence test (1 - alpha).
`digits`	Number of significant digits to keep.
`pdigits`	Number of decimal digits to keep for p values. If `NULL`, the value of `digits` is used.
`...`	Additional arguments are passed to the `format()` function (e.g., `big.marks`, `scientific`). See `?format`

References

Astier, Nicolas, and Frank A. Wolak. Credible Numbers: A Procedure for Reporting Statistical Precision in Parameter Estimates. No. w32124. National Bureau of Economic Research, 2024.

Examples

library(modelsummary)
mod <- lm(mpg ~ hp, mtcars)

# Default equivalence-based formatting
modelsummary(mod, fmt = fmt_equivalence())

# alpha = 0.2
modelsummary(mod, fmt = fmt_equivalence(conf_level = .8))

# default equivalence, but with alternative significant digits for other statistics
modelsummary(mod, fmt = fmt_equivalence(digits = 5))

library(modelsummary)
mod <- lm(mpg ~ hp, mtcars)

# Default equivalence-based formatting
modelsummary(mod, fmt = fmt_equivalence())

# alpha = 0.2
modelsummary(mod, fmt = fmt_equivalence(conf_level = .8))

# default equivalence, but with alternative significant digits for other statistics
modelsummary(mod, fmt = fmt_equivalence(digits = 5))

Rounding using scientific notation

Description

Rounding using scientific notation

Usage

fmt_sci(digits = 3, ...)
fmt_sci(digits = 3, ...)

Arguments

`digits`	a positive integer indicating how many significant digits are to be used for numeric and complex `x`.
`...`	additional arguments passed to `format()`.

Rounding with significant digits in the `fmt` argument

Description

The number of decimal digits to keep after the decimal is assessed

Usage

fmt_significant(digits = 3, ...)
fmt_significant(digits = 3, ...)

Arguments

`digits`	Number of significant digits to keep.
`...`	Additional arguments are passed to the `format()` function (e.g., `big.marks`, `scientific`). See `?format`

Rounding with the `sprintf()` function in the `fmt` argument

Description

Rounding with the sprintf() function in the fmt argument

Usage

fmt_sprintf(fmt)
fmt_sprintf(fmt)

Arguments

fmt

A string to control sprintf(), such as "%.3f" to keep 3 decimal digits. See ?sprintf

Rounding with decimal digits on a per-statistic basis in the `fmt` argument for `modelsummary()`

Description

Rounding with decimal digits on a per-statistic basis in the fmt argument for modelsummary()

Usage

fmt_statistic(..., default = 3)
fmt_statistic(..., default = 3)

Arguments

`...`	Statistic names and `fmt` value
`default`	Number of decimal digits to keep for unspecified terms

Rounding with decimal digits on a per-term basis in the `fmt` argument for `modelsummary()`

Description

Rounding with decimal digits on a per-term basis in the fmt argument for modelsummary()

Usage

fmt_term(..., default = 3)
fmt_term(..., default = 3)

Arguments

`...`	Term names and `fmt` value
`default`	Number of decimal digits to keep for unspecified terms

Extract model estimates in a tidy format.

Description

A unified approach to extract results from a wide variety of models. For some models get_estimates attaches useful attributes to the output. You can access this information by calling the attributes function: attributes(get_estimates(model))

Usage

get_estimates(
  model,
  conf_level = 0.95,
  vcov = NULL,
  shape = NULL,
  coef_rename = FALSE,
  ...
)
get_estimates(
  model,
  conf_level = 0.95,
  vcov = NULL,
  shape = NULL,
  coef_rename = FALSE,
  ...
)

Arguments

`model`	a single model object
`conf_level`	numeric value between 0 and 1. confidence level to use for confidence intervals. Setting this argument to `NULL` does not extract confidence intervals, which can be faster for some models.
`vcov`	robust standard errors and other manual statistics. The `vcov` argument accepts six types of input (see the 'Details' and 'Examples' sections below): NULL returns the default uncertainty estimates of the model object string, vector, or (named) list of strings. "iid", "classical", and "constant" are aliases for `NULL`, which returns the model's default uncertainty estimates. The strings "HC", "HC0", "HC1" (alias: "stata"), "HC2", "HC3" (alias: "robust"), "HC4", "HC4m", "HC5", "HAC", "NeweyWest", "Andrews", "panel-corrected", "outer-product", and "weave" use variance-covariance matrices computed using functions from the `sandwich` package, or equivalent method. "BS", "bootstrap", "residual", "mammen", "webb", "xy", "wild" use the `sandwich::vcovBS()`. The behavior of those functions can (and sometimes must) be altered by passing arguments to `sandwich` directly from `modelsummary` through the ellipsis (`...`), but it is safer to define your own custom functions as described in the next bullet. function or (named) list of functions which return variance-covariance matrices with row and column names equal to the names of your coefficient estimates (e.g., `stats::vcov`, `sandwich::vcovHC`, `function(x) vcovPC(x, cluster="country")`). formula or (named) list of formulas with the cluster variable(s) on the right-hand side (e.g., ~clusterid). named list of `length(models)` variance-covariance matrices with row and column names equal to the names of your coefficient estimates. a named list of length(models) vectors with names equal to the names of your coefficient estimates. See 'Examples' section below. Warning: since this list of vectors can include arbitrary strings or numbers, `modelsummary` cannot automatically calculate p values. The `stars` argument may thus use incorrect significance thresholds when `vcov` is a list of vectors.
`shape`	`NULL`, formula, or string which determines the shape of a table. `NULL`: Default shape with terms in rows and models in columns. Formula: The left side determines what appears on rows, and the right side determines what appears on columns. The formula can include one or more group identifier(s) to display related terms together, which can be useful for models with multivariate outcomes or grouped coefficients (See examples section below). The group identifier(s) must be column names produced by: `get_estimates(model)`. The group identifier(s) can be combined with the term identifier in a single column by using the colon to represent an interaction. If an incomplete formula is supplied (e.g., `~statistic`), `modelsummary` tries to complete it automatically. Goodness-of-fit statistics are only appended to the bottom of the table when `model` is on the right hand side of the formula (i.e., columns). Potential `shape` values include: `term + statistic ~ model`: default `term ~ model + statistic`: statistics in separate columns `model + statistic ~ term`: models in rows and terms in columns `term + response + statistic ~ model`: term and group id in separate columns `term : response + statistic ~ model`: term and group id in a single column `term ~ response` String: "cbind", "rbind", "rcollapse" "cbind": side-by-side models with autmoatic spanning column headers to group models (`tinytable` only feature). "rbind" or "rcollapse": "panels" or "stacks" of regression models. the `models` argument must be a (potentially named) nested list of models. Unnamed nested list with 2 panels: `list(list(model1, model2), list(model3, model4))` Named nested list with 2 panels: `list("Panel A" = list(model1, model2), "Panel B" = list(model3, model4))` Named panels and named models: `list("Panel A" = list("(I)" = model1, "(II)" = model2), "Panel B" = list("(I)" = model3, "(II)" = model4))` "rbind": Bind the rows of independent regression tables "rcollapse": Bind the rows of regression tables and create a panel at the bottom where we "collapse" goodness-of-fit statistics which are identical across models.
`coef_rename`	logical, named or unnamed character vector, or function Logical: TRUE renames variables based on the "label" attribute of each column. See the Example section below. Unnamed character vector of length equal to the number of coefficients in the final table, after `coef_omit` is applied. Named character vector: Values refer to the variable names that will appear in the table. Names refer to the original term names stored in the model object. Ex: c("hp:mpg"="hp X mpg") Function: Accepts a character vector of the model's term names and returns a named vector like the one described above. The `modelsummary` package supplies a `coef_rename()` function which can do common cleaning tasks: `modelsummary(model, coef_rename = coef_rename)`
`...`	all other arguments are passed through to three functions. See the documentation of these functions for lists of available arguments. parameters::model_parameters extracts parameter estimates. Available arguments depend on model type, but include: `standardize`, `include_reference`, `centrality`, `dispersion`, `test`, `ci_method`, `prior`, `diagnostic`, `rope_range`, `power`, `cluster`, etc. performance::model_performance extracts goodness-of-fit statistics. Available arguments depend on model type, but include: `metrics`, `estimator`, etc. tinytable::tt, kableExtra::kbl or gt::gt draw tables, depending on the value of the `output` argument. For example, by default `modelsummary` creates tables with tinytable::tt, which accepts a `width` and `theme` arguments.

Extract goodness-of-fit statistics a tidy format.

Description

A unified approach to extract results from a wide variety of models. For some models get_gof attaches useful attributes to the output. You can access this information by calling the attributes function: attributes(get_estimates(model))

Usage

get_gof(model, gof_function = NULL, vcov_type = NULL, ...)
get_gof(model, gof_function = NULL, vcov_type = NULL, ...)

Arguments

`model`	a single model object
`gof_function`	function which accepts a model object in the `model` argument and returns a 1-row `data.frame` with one custom goodness-of-fit statistic per column.
`vcov_type`	string vcov type to add at the bottom of the table
`...`	all other arguments are passed through to three functions. See the documentation of these functions for lists of available arguments. parameters::model_parameters extracts parameter estimates. Available arguments depend on model type, but include: `standardize`, `include_reference`, `centrality`, `dispersion`, `test`, `ci_method`, `prior`, `diagnostic`, `rope_range`, `power`, `cluster`, etc. performance::model_performance extracts goodness-of-fit statistics. Available arguments depend on model type, but include: `metrics`, `estimator`, etc. tinytable::tt, kableExtra::kbl or gt::gt draw tables, depending on the value of the `output` argument. For example, by default `modelsummary` creates tables with tinytable::tt, which accepts a `width` and `theme` arguments.

Data.frame used to clean up and format goodness-of-fit statistics

Description

By default, this data frame is passed to the 'gof_map' argument of the 'modelsummary' function. Users can modify this data frame to customize the list of statistics to display and their format. See example below.

Usage

gof_map
gof_map

Format

data.frame with 4 columns of character data: raw, clean, fmt, omit

Examples

if (identical(Sys.getenv("pkgdown"),  "true")) {

library(modelsummary)
mod <- lm(wt ~ drat, data = mtcars)
gm <- modelsummary::gof_map
gm$omit[gm$raw == 'deviance'] <- FALSE
gm$fmt[gm$raw == 'r.squared'] <- "%.5f"
modelsummary(mod, gof_map = gm)
}

if (identical(Sys.getenv("pkgdown"),  "true")) {

library(modelsummary)
mod <- lm(wt ~ drat, data = mtcars)
gm <- modelsummary::gof_map
gm$omit[gm$raw == 'deviance'] <- FALSE
gm$fmt[gm$raw == 'r.squared'] <- "%.5f"
modelsummary(mod, gof_map = gm)
}

Model Summary Plots with Estimates and Confidence Intervals

Description

Dot-Whisker plot of coefficient estimates with confidence intervals. For more information, see the Details and Examples sections below, and the vignettes on the modelsummary website: https://modelsummary.com/

modelplot Vignette.

Usage

modelplot(
  models,
  conf_level = 0.95,
  coef_map = NULL,
  coef_omit = NULL,
  coef_rename = NULL,
  vcov = NULL,
  exponentiate = FALSE,
  add_rows = NULL,
  facet = FALSE,
  draw = TRUE,
  background = NULL,
  ...
)
modelplot(
  models,
  conf_level = 0.95,
  coef_map = NULL,
  coef_omit = NULL,
  coef_rename = NULL,
  vcov = NULL,
  exponentiate = FALSE,
  add_rows = NULL,
  facet = FALSE,
  draw = TRUE,
  background = NULL,
  ...
)

Arguments

`models`	a model, (named) list of models, or nested list of models. Single model: `modelsummary(model)` Unnamed list of models: `modelsummary(list(model1, model2))` Models are labelled automatically. The default label style can be altered by setting a global option. See below. Named list of models: `modelsummary(list("A"=model1, "B"=model2))` Models are labelled using the list names. Nested list of models: When using the `shape` argument with "rbind", "rcollapse", or "cbind" values, `models` can be a nested list of models to display "panels" or "stacks" of regression models. See the `shape` argument documentation and examples below.
`conf_level`	numeric value between 0 and 1. confidence level to use for confidence intervals. Setting this argument to `NULL` does not extract confidence intervals, which can be faster for some models.
`coef_map`	character vector. Subset, rename, and reorder coefficients. Coefficients omitted from this vector are omitted from the table. The order of the vector determines the order of the table. `coef_map` can be a named or an unnamed character vector. If `coef_map` is a named vector, its values define the labels that must appear in the table, and its names identify the original term names stored in the model object: `c("hp:mpg"="HPxM/G")`. See Examples section below.
`coef_omit`	integer vector or regular expression to identify which coefficients to omit (or keep) from the table. Positive integers determine which coefficients to omit. Negative integers determine which coefficients to keep. A regular expression can be used to omit coefficients, and perl-compatible "negative lookaheads" can be used to specify which coefficients to keep in the table. Examples: c(2, 3, 5): omits the second, third, and fifth coefficients. c(-2, -3, -5): negative values keep the second, third, and fifth coefficients. `"ei"`: omit coefficients matching the "ei" substring. `"^Volume$"`: omit the "Volume" coefficient. `"ei\|rc"`: omit coefficients matching either the "ei" or the "rc" substrings. `"^(?!Vol)"`: keep coefficients starting with "Vol" (inverse match using a negative lookahead). `"^(?!.ei)"`: keep coefficients matching the "ei" substring. `"^(?!.ei\|.*pt)"`: keep coefficients matching either the "ei" or the "pt" substrings. See the Examples section below for complete code.
`coef_rename`	logical, named or unnamed character vector, or function Logical: TRUE renames variables based on the "label" attribute of each column. See the Example section below. Unnamed character vector of length equal to the number of coefficients in the final table, after `coef_omit` is applied. Named character vector: Values refer to the variable names that will appear in the table. Names refer to the original term names stored in the model object. Ex: c("hp:mpg"="hp X mpg") Function: Accepts a character vector of the model's term names and returns a named vector like the one described above. The `modelsummary` package supplies a `coef_rename()` function which can do common cleaning tasks: `modelsummary(model, coef_rename = coef_rename)`
`vcov`	robust standard errors and other manual statistics. The `vcov` argument accepts six types of input (see the 'Details' and 'Examples' sections below): NULL returns the default uncertainty estimates of the model object string, vector, or (named) list of strings. "iid", "classical", and "constant" are aliases for `NULL`, which returns the model's default uncertainty estimates. The strings "HC", "HC0", "HC1" (alias: "stata"), "HC2", "HC3" (alias: "robust"), "HC4", "HC4m", "HC5", "HAC", "NeweyWest", "Andrews", "panel-corrected", "outer-product", and "weave" use variance-covariance matrices computed using functions from the `sandwich` package, or equivalent method. "BS", "bootstrap", "residual", "mammen", "webb", "xy", "wild" use the `sandwich::vcovBS()`. The behavior of those functions can (and sometimes must) be altered by passing arguments to `sandwich` directly from `modelsummary` through the ellipsis (`...`), but it is safer to define your own custom functions as described in the next bullet. function or (named) list of functions which return variance-covariance matrices with row and column names equal to the names of your coefficient estimates (e.g., `stats::vcov`, `sandwich::vcovHC`, `function(x) vcovPC(x, cluster="country")`). formula or (named) list of formulas with the cluster variable(s) on the right-hand side (e.g., ~clusterid). named list of `length(models)` variance-covariance matrices with row and column names equal to the names of your coefficient estimates. a named list of length(models) vectors with names equal to the names of your coefficient estimates. See 'Examples' section below. Warning: since this list of vectors can include arbitrary strings or numbers, `modelsummary` cannot automatically calculate p values. The `stars` argument may thus use incorrect significance thresholds when `vcov` is a list of vectors.
`exponentiate`	TRUE, FALSE, or logical vector of length equal to the number of models. If TRUE, the `estimate`, `conf.low`, and `conf.high` statistics are exponentiated, and the `std.error` is transformed to `exp(estimate)*std.error`.
`add_rows`	a data.frame (or tibble) with the same number of columns as your main table. By default, rows are appended to the bottom of the table. You can define a "position" attribute of integers to set the row positions. See Examples section below.
`facet`	TRUE or FALSE. When the 'models' argument includes several model objects, TRUE draws terms in separate facets, and FALSE draws terms side-by-side (dodged).
`draw`	TRUE returns a 'ggplot2' object, FALSE returns the data.frame used to draw the plot.
`background`	A list of 'ggplot2' geoms to add to the background of the plot. This is especially useful to display annotations "behind" the 'geom_pointrange' that 'modelplot' draws.
`...`	all other arguments are passed through to three functions. See the documentation of these functions for lists of available arguments. parameters::model_parameters extracts parameter estimates. Available arguments depend on model type, but include: `standardize`, `include_reference`, `centrality`, `dispersion`, `test`, `ci_method`, `prior`, `diagnostic`, `rope_range`, `power`, `cluster`, etc. performance::model_performance extracts goodness-of-fit statistics. Available arguments depend on model type, but include: `metrics`, `estimator`, etc. tinytable::tt, kableExtra::kbl or gt::gt draw tables, depending on the value of the `output` argument. For example, by default `modelsummary` creates tables with tinytable::tt, which accepts a `width` and `theme` arguments.

Examples

library(modelsummary)

# single model
mod <- lm(hp ~ vs + drat, mtcars)
modelplot(mod)

# omit terms with string matches or regexes
modelplot(mod, coef_omit = 'Interc')

# rename, reorder and subset with 'coef_map'
cm <- c('vs' = 'V-shape engine',
  'drat' = 'Rear axle ratio')
modelplot(mod, coef_map = cm)

# several models
models <- list()
models[['Small model']] <- lm(hp ~ vs, mtcars)
models[['Medium model']] <- lm(hp ~ vs + factor(cyl), mtcars)
models[['Large model']] <- lm(hp ~ vs + drat + factor(cyl), mtcars)
modelplot(models)

# add_rows: add an empty reference category

mod <- lm(hp ~ factor(cyl), mtcars)

add_rows = data.frame(
  term = "factory(cyl)4",
  model = "(1)",
  estimate = NA)
attr(add_rows, "position") = 3
modelplot(mod, add_rows = add_rows)


# customize your plots with 'ggplot2' functions
library(ggplot2)

modelplot(models) +
  scale_color_brewer(type = 'qual') +
  theme_classic()

# pass arguments to 'geom_pointrange' through the ... ellipsis
modelplot(mod, color = 'red', size = 1, fatten = .5)

# add geoms to the background, behind geom_pointrange
b <- list(geom_vline(xintercept = 0, color = 'orange'),
  annotate("rect", alpha = .1,
    xmin = -.5, xmax = .5,
    ymin = -Inf, ymax = Inf),
  geom_point(aes(y = term, x = estimate), alpha = .3,
    size = 10, color = 'red', shape = 'square'))
modelplot(mod, background = b)

# logistic regression example
df <- as.data.frame(Titanic)
mod_titanic <- glm(
  Survived ~ Class + Sex,
  family = binomial,
  weight = Freq,
  data = df
)

# displaying odds ratio using a log scale
modelplot(mod_titanic, exponentiate = TRUE) +
  scale_x_log10() +
  xlab("Odds Ratios and 95% confidence intervals")

References

Arel-Bundock V (2022). “modelsummary: Data and Model Summaries in R.” Journal of Statistical Software, 103(1), 1-23. doi:10.18637/jss.v103.i01.'

Model Summary Tables

Description

Create beautiful and customizable tables to summarize several statistical models side-by-side. This function supports dozens of statistical models, and it can produce tables in HTML, LaTeX, Word, Markdown, Typst, PDF, PowerPoint, Excel, RTF, JPG, or PNG. The appearance of the tables can be customized extensively by specifying the output argument, and by using functions from one of the supported table customization packages: tinytable, kableExtra, gt, flextable, huxtable, DT. For more information, see the Details and Examples sections below, and the vignettes on the modelsummary website: https://modelsummary.com/

Usage

modelsummary(
  models,
  output = "default",
  fmt = 3,
  estimate = "estimate",
  statistic = "std.error",
  vcov = NULL,
  conf_level = 0.95,
  exponentiate = FALSE,
  stars = FALSE,
  shape = term + statistic ~ model,
  coef_map = NULL,
  coef_omit = NULL,
  coef_rename = FALSE,
  gof_map = NULL,
  gof_omit = NULL,
  gof_function = NULL,
  group_map = NULL,
  add_columns = NULL,
  add_rows = NULL,
  align = NULL,
  notes = NULL,
  title = NULL,
  escape = TRUE,
  ...
)
modelsummary(
  models,
  output = "default",
  fmt = 3,
  estimate = "estimate",
  statistic = "std.error",
  vcov = NULL,
  conf_level = 0.95,
  exponentiate = FALSE,
  stars = FALSE,
  shape = term + statistic ~ model,
  coef_map = NULL,
  coef_omit = NULL,
  coef_rename = FALSE,
  gof_map = NULL,
  gof_omit = NULL,
  gof_function = NULL,
  group_map = NULL,
  add_columns = NULL,
  add_rows = NULL,
  align = NULL,
  notes = NULL,
  title = NULL,
  escape = TRUE,
  ...
)

Arguments

`models`	a model, (named) list of models, or nested list of models. Single model: `modelsummary(model)` Unnamed list of models: `modelsummary(list(model1, model2))` Models are labelled automatically. The default label style can be altered by setting a global option. See below. Named list of models: `modelsummary(list("A"=model1, "B"=model2))` Models are labelled using the list names. Nested list of models: When using the `shape` argument with "rbind", "rcollapse", or "cbind" values, `models` can be a nested list of models to display "panels" or "stacks" of regression models. See the `shape` argument documentation and examples below.
`output`	filename or object type (character string) Supported filename extensions: .docx, .html, .tex, .md, .txt, .csv, .xlsx, .png, .jpg Supported object types: "default", "html", "markdown", "latex", "latex_tabular", "typst", "data.frame", "tinytable", "gt", "kableExtra", "huxtable", "flextable", "DT", "jupyter". The "modelsummary_list" value produces a lightweight object which can be saved and fed back to the `modelsummary` function. The "default" output format can be set to "tinytable", "kableExtra", "gt", "flextable", "huxtable", "DT", or "markdown" If the user does not choose a default value, the packages listed above are tried in sequence. Session-specific configuration: `options("modelsummary_factory_default" = "gt")` Persistent configuration: `config_modelsummary(output = "markdown")` Warning: Users should not supply a file name to the `output` argument if they intend to customize the table with external packages. See the 'Details' section. LaTeX compilation requires the `booktabs` and `siunitx` packages, but `siunitx` can be disabled or replaced with global options. See the 'Details' section.
`fmt`	how to format numeric values: integer, user-supplied function, or `modelsummary` function. Integer: Number of decimal digits User-supplied functions: Any function which accepts a numeric vector and returns a character vector of the same length. `modelsummary` functions: `fmt = fmt_significant(2)`: Two significant digits (at the term-level) `fmt = fmt_decimal(digits = 2, pdigits = 3)`: Decimal digits for estimate and p values `fmt = fmt_sprintf("%.3f")`: See `?sprintf` `fmt = fmt_term("(Intercept)" = 1, "X" = 2)`: Format terms differently `fmt = fmt_statistic("estimate" = 1, "r.squared" = 6)`: Format statistics differently. `fmt = fmt_identity()`: unformatted raw values string: Note on LaTeX output: To ensure proper typography, all numeric entries are enclosed in the `⁠\num{}⁠` command, which requires the `siunitx` package to be loaded in the LaTeX preamble. This behavior can be altered with global options. See the 'Details' section.
`estimate`	a single string or a character vector of length equal to the number of models. Valid entries include any column name of the data.frame produced by `get_estimates(model)`, and strings with curly braces compatible with the `glue` package format. Examples: `"estimate"` `"{estimate} ({std.error}){stars}"` `"{estimate} [{conf.low}, {conf.high}]"`
`statistic`	vector of strings or `glue` strings which select uncertainty statistics to report vertically below the estimate. NULL omits all uncertainty statistics. "conf.int", "std.error", "statistic", "p.value", "conf.low", "conf.high", or any column name produced by `get_estimates(model)` `glue` package strings with braces, with or without R functions, such as: `"{p.value} [{conf.low}, {conf.high}]"` `"Std.Error: {std.error}"` `"{exp(estimate) * std.error}"` Numbers are automatically rounded and converted to strings. To apply functions to their numeric values, as in the last `glue` example, users must set `fmt=NULL`. Parentheses are added automatically unless the string includes `glue` curly braces `{}`. Notes: The names of the `statistic` are used a column names when using the `shape` argument to display statistics as columns: `statistic=c("p"="p.value", "["="conf.low", "]"="conf.high")` Some statistics are not supported for all models. See column names in `get_estimates(model)`, and visit the website to learn how to add custom statistics.
`vcov`	robust standard errors and other manual statistics. The `vcov` argument accepts six types of input (see the 'Details' and 'Examples' sections below): NULL returns the default uncertainty estimates of the model object string, vector, or (named) list of strings. "iid", "classical", and "constant" are aliases for `NULL`, which returns the model's default uncertainty estimates. The strings "HC", "HC0", "HC1" (alias: "stata"), "HC2", "HC3" (alias: "robust"), "HC4", "HC4m", "HC5", "HAC", "NeweyWest", "Andrews", "panel-corrected", "outer-product", and "weave" use variance-covariance matrices computed using functions from the `sandwich` package, or equivalent method. "BS", "bootstrap", "residual", "mammen", "webb", "xy", "wild" use the `sandwich::vcovBS()`. The behavior of those functions can (and sometimes must) be altered by passing arguments to `sandwich` directly from `modelsummary` through the ellipsis (`...`), but it is safer to define your own custom functions as described in the next bullet. function or (named) list of functions which return variance-covariance matrices with row and column names equal to the names of your coefficient estimates (e.g., `stats::vcov`, `sandwich::vcovHC`, `function(x) vcovPC(x, cluster="country")`). formula or (named) list of formulas with the cluster variable(s) on the right-hand side (e.g., ~clusterid). named list of `length(models)` variance-covariance matrices with row and column names equal to the names of your coefficient estimates. a named list of length(models) vectors with names equal to the names of your coefficient estimates. See 'Examples' section below. Warning: since this list of vectors can include arbitrary strings or numbers, `modelsummary` cannot automatically calculate p values. The `stars` argument may thus use incorrect significance thresholds when `vcov` is a list of vectors.
`conf_level`	numeric value between 0 and 1. confidence level to use for confidence intervals. Setting this argument to `NULL` does not extract confidence intervals, which can be faster for some models.
`exponentiate`	TRUE, FALSE, or logical vector of length equal to the number of models. If TRUE, the `estimate`, `conf.low`, and `conf.high` statistics are exponentiated, and the `std.error` is transformed to `exp(estimate)*std.error`.
`stars`	to indicate statistical significance FALSE (default): no significance stars. TRUE: `c("+" = .1, "" = .05, "" = .01, "*" = 0.001)` Named numeric vector for custom stars such as `c('' = .1, '+' = .05)` Note: a legend will not be inserted at the bottom of the table when the `estimate` or `statistic` arguments use "glue strings" with `{stars}`.
`shape`	`NULL`, formula, or string which determines the shape of a table. `NULL`: Default shape with terms in rows and models in columns. Formula: The left side determines what appears on rows, and the right side determines what appears on columns. The formula can include one or more group identifier(s) to display related terms together, which can be useful for models with multivariate outcomes or grouped coefficients (See examples section below). The group identifier(s) must be column names produced by: `get_estimates(model)`. The group identifier(s) can be combined with the term identifier in a single column by using the colon to represent an interaction. If an incomplete formula is supplied (e.g., `~statistic`), `modelsummary` tries to complete it automatically. Goodness-of-fit statistics are only appended to the bottom of the table when `model` is on the right hand side of the formula (i.e., columns). Potential `shape` values include: `term + statistic ~ model`: default `term ~ model + statistic`: statistics in separate columns `model + statistic ~ term`: models in rows and terms in columns `term + response + statistic ~ model`: term and group id in separate columns `term : response + statistic ~ model`: term and group id in a single column `term ~ response` String: "cbind", "rbind", "rcollapse" "cbind": side-by-side models with autmoatic spanning column headers to group models (`tinytable` only feature). "rbind" or "rcollapse": "panels" or "stacks" of regression models. the `models` argument must be a (potentially named) nested list of models. Unnamed nested list with 2 panels: `list(list(model1, model2), list(model3, model4))` Named nested list with 2 panels: `list("Panel A" = list(model1, model2), "Panel B" = list(model3, model4))` Named panels and named models: `list("Panel A" = list("(I)" = model1, "(II)" = model2), "Panel B" = list("(I)" = model3, "(II)" = model4))` "rbind": Bind the rows of independent regression tables "rcollapse": Bind the rows of regression tables and create a panel at the bottom where we "collapse" goodness-of-fit statistics which are identical across models.
`coef_map`	character vector. Subset, rename, and reorder coefficients. Coefficients omitted from this vector are omitted from the table. The order of the vector determines the order of the table. `coef_map` can be a named or an unnamed character vector. If `coef_map` is a named vector, its values define the labels that must appear in the table, and its names identify the original term names stored in the model object: `c("hp:mpg"="HPxM/G")`. See Examples section below.
`coef_omit`	integer vector or regular expression to identify which coefficients to omit (or keep) from the table. Positive integers determine which coefficients to omit. Negative integers determine which coefficients to keep. A regular expression can be used to omit coefficients, and perl-compatible "negative lookaheads" can be used to specify which coefficients to keep in the table. Examples: c(2, 3, 5): omits the second, third, and fifth coefficients. c(-2, -3, -5): negative values keep the second, third, and fifth coefficients. `"ei"`: omit coefficients matching the "ei" substring. `"^Volume$"`: omit the "Volume" coefficient. `"ei\|rc"`: omit coefficients matching either the "ei" or the "rc" substrings. `"^(?!Vol)"`: keep coefficients starting with "Vol" (inverse match using a negative lookahead). `"^(?!.ei)"`: keep coefficients matching the "ei" substring. `"^(?!.ei\|.*pt)"`: keep coefficients matching either the "ei" or the "pt" substrings. See the Examples section below for complete code.
`coef_rename`	logical, named or unnamed character vector, or function Logical: TRUE renames variables based on the "label" attribute of each column. See the Example section below. Unnamed character vector of length equal to the number of coefficients in the final table, after `coef_omit` is applied. Named character vector: Values refer to the variable names that will appear in the table. Names refer to the original term names stored in the model object. Ex: c("hp:mpg"="hp X mpg") Function: Accepts a character vector of the model's term names and returns a named vector like the one described above. The `modelsummary` package supplies a `coef_rename()` function which can do common cleaning tasks: `modelsummary(model, coef_rename = coef_rename)`
`gof_map`	rename, reorder, and omit goodness-of-fit statistics and other model information. This argument accepts 4 types of values: NULL (default): the `modelsummary::gof_map` dictionary is used for formatting, and all unknown statistic are included. character vector: "all", "none", or a vector of statistics such as `c("rmse", "nobs", "r.squared")`. Elements correspond to colnames in the data.frame produced by `get_gof(model)`. The `modelsummary::gof_map` default dictionary is used to format and rename statistics. NA: excludes all statistics from the bottom part of the table. data.frame with 3 columns named "raw", "clean", "fmt". Unknown statistics are omitted. See the 'Examples' section below. The `fmt` column in this data frame only accepts integers. For more flexibility, use a list of lists, as described in the next bullet. list of lists, each of which includes 3 elements named "raw", "clean", "fmt". Unknown statistics are omitted. See the 'Examples section below'.
`gof_omit`	string regular expression (perl-compatible) used to determine which statistics to omit from the bottom section of the table. A "negative lookahead" can be used to specify which statistics to keep in the table. Examples: `"IC"`: omit statistics matching the "IC" substring. `"BIC\|AIC"`: omit statistics matching the "AIC" or "BIC" substrings. `"^(?!.*IC)"`: keep statistics matching the "IC" substring.
`gof_function`	function which accepts a model object in the `model` argument and returns a 1-row `data.frame` with one custom goodness-of-fit statistic per column.
`group_map`	named or unnamed character vector. Subset, rename, and reorder coefficient groups specified a grouping variable specified in the `shape` argument formula. This argument behaves like `coef_map`.
`add_columns`	a data.frame (or tibble) with the same number of rows as #' your main table. By default, rows are appended to the bottom of the table. You can define a "position" attribute of integers to set the columns positions. See Examples section below.
`add_rows`	a data.frame (or tibble) with the same number of columns as your main table. By default, rows are appended to the bottom of the table. You can define a "position" attribute of integers to set the row positions. See Examples section below.
`align`	A string with a number of characters equal to the number of columns in the table (e.g., `align = "lcc"`). Valid characters: l, c, r, d. "l": left-aligned column "c": centered column "r": right-aligned column "d": dot-aligned column. For LaTeX/PDF output, this option requires at least version 3.0.25 of the siunitx LaTeX package. See the LaTeX preamble help section below for commands to insert in your LaTeX preamble.
`notes`	list or vector of notes to append to the bottom of the table.
`title`	string. Cross-reference labels should be added with Quarto or Rmarkdown chunk options when applicable. When saving standalone LaTeX files, users can add a label such as `⁠\\label{tab:mytable}⁠` directly to the title string, while also specifying `escape=FALSE`.
`escape`	boolean TRUE escapes or substitutes LaTeX/HTML characters which could prevent the file from compiling/displaying. `TRUE` escapes all cells, captions, and notes. Users can have more fine-grained control by setting `escape=FALSE` and using an external command such as: `modelsummary(model, "latex") \|> tinytable::format_tt(tab, j=1:5, escape=TRUE)`
`...`	all other arguments are passed through to three functions. See the documentation of these functions for lists of available arguments. parameters::model_parameters extracts parameter estimates. Available arguments depend on model type, but include: `standardize`, `include_reference`, `centrality`, `dispersion`, `test`, `ci_method`, `prior`, `diagnostic`, `rope_range`, `power`, `cluster`, etc. performance::model_performance extracts goodness-of-fit statistics. Available arguments depend on model type, but include: `metrics`, `estimator`, etc. tinytable::tt, kableExtra::kbl or gt::gt draw tables, depending on the value of the `output` argument. For example, by default `modelsummary` creates tables with tinytable::tt, which accepts a `width` and `theme` arguments.

Details

`output`

The modelsummary_list output is a lightweight format which can be used to save model results, so they can be fed back to modelsummary later to avoid extracting results again.

When a file name with a valid extension is supplied to the output argument, the table is written immediately to file. If you want to customize your table by post-processing it with an external package, you need to choose a different output format and saving mechanism. Unfortunately, the approach differs from package to package:

tinytable: set output="tinytable", post-process your table, and use the tinytable::save_tt function.
gt: set output="gt", post-process your table, and use the gt::gtsave function.
kableExtra: set output to your destination format (e.g., "latex", "html", "markdown"), post-process your table, and use kableExtra::save_kable function.

`vcov`

To use a string such as "robust" or "HC0", your model must be supported by the sandwich package. This includes objects such as: lm, glm, survreg, coxph, mlogit, polr, hurdle, zeroinfl, and more.

NULL, "classical", "iid", and "constant" are aliases which do not modify uncertainty estimates and simply report the default standard errors stored in the model object.

One-sided formulas such as ~clusterid are passed to the sandwich::vcovCL function.

Matrices and functions producing variance-covariance matrices are first passed to lmtest. If this does not work, modelsummary attempts to take the square root of the diagonal to adjust "std.error", but the other uncertainty estimates are not be adjusted.

Numeric vectors are formatted according to fmt and placed in brackets. Character vectors printed as given, without parentheses.

If your model type is supported by the lmtest package, the vcov argument will try to use that package to adjust all the uncertainty estimates, including "std.error", "statistic", "p.value", and "conf.int". If your model is not supported by lmtest, only the "std.error" will be adjusted by, for example, taking the square root of the matrix's diagonal.

Value

a regression table in a format determined by the output argument.

Version 2.0.0, kableExtra, and tinytable

Since version 2.0.0, modelsummary uses tinytable as its default table-drawing backend. Learn more at: https://vincentarelbundock.github.io/tinytable/",

Revert to kableExtra for one session:

options(modelsummary_factory_default = 'kableExtra') options(modelsummary_factory_latex = 'kableExtra') options(modelsummary_factory_html = 'kableExtra')

Global Options

The behavior of modelsummary can be modified by setting global options. For example:

options(modelsummary_model_labels = "roman")

The rest of this section describes each of the options above.

Model labels: default column names

These global option changes the style of the default column headers:

options(modelsummary_model_labels = "roman")
options(modelsummary_panel_labels = "roman")

The supported styles are: "model", "panel", "arabic", "letters", "roman", "(arabic)", "(letters)", "(roman)"

The panel-specific option is only used when shape="rbind"

Table-making packages

Table themes

Change the look of tables in an automated and replicable way, using the modelsummary theming functionality. See the vignette: https://modelsummary.com/articles/appearance.html

modelsummary_theme_gt
modelsummary_theme_kableExtra
modelsummary_theme_huxtable
modelsummary_theme_flextable
modelsummary_theme_dataframe

Model extraction functions

options(modelsummary_get = "easystats")

options(modelsummary_get = "broom")

options(modelsummary_get = "all")

Formatting numeric entries

options(modelsummary_format_numeric_latex = "plain")

options(modelsummary_format_numeric_latex = "mathmode")

A similar option can be used to display numerical entries using MathJax in HTML tables:

options(modelsummary_format_numeric_html = "mathjax")

LaTeX preamble

\usepackage{tabularray}
\usepackage{float}
\usepackage{graphicx}
\usepackage[normalem]{ulem}
\UseTblrLibrary{booktabs}
\UseTblrLibrary{siunitx}
\newcommand{\tinytableTabularrayUnderline}[1]{\underline{#1}}
\newcommand{\tinytableTabularrayStrikeout}[1]{\sout{#1}}
\NewTableCommand{\tinytableDefineColor}[3]{\definecolor{#1}{#2}{#3}}

Parallel computation

It can take a long time to compute and extract summary statistics from certain models (e.g., Bayesian). In those cases, users can parallelize the process. Since parallelization occurs at the model level, no speedup is available for tables with a single model. Users on mac or linux can launch parallel computation using the built-in parallel package. All they need to do is supply a mc.cores argument which will be pushed forward to the parallel::mclapply function:

modelsummary(model_list, mc.cores = 5)

All users can also use the future.apply package to parallelize model summaries. For example, to use 4 cores to extract results:

library(future.apply)
plan(multicore, workers = 4)
options("modelsummary_future" = TRUE)
modelsummary(model_list)

Note that the "multicore" plan only parallelizes under mac or linux. Windows users can use plan(multisession) instead. However, note that the first time modelsummary() is called under multisession can be a fair bit longer, because of extra costs in passing data to and loading required packages on to workers. Subsequent calls to modelsummary() will often be much faster.

Some users have reported difficult to reproduce errors when using the future package with some packages. The future parallelization in modelsummary can be disabled by calling:

options("modelsummary_future" = FALSE)

References

Arel-Bundock V (2022). “modelsummary: Data and Model Summaries in R.” Journal of Statistical Software, 103(1), 1-23. doi:10.18637/jss.v103.i01.'

Examples


# The `modelsummary` website includes \emph{many} examples and tutorials:
# https://modelsummary.com

library(modelsummary)

# load data and estimate models
utils::data(trees)
models <- list()
models[["Bivariate"]] <- lm(Girth ~ Height, data = trees)
models[["Multivariate"]] <- lm(Girth ~ Height + Volume, data = trees)

# simple table
modelsummary(models)

# statistic
modelsummary(models, statistic = NULL)

modelsummary(models, statistic = "p.value")

modelsummary(models, statistic = "statistic")

modelsummary(models, statistic = "conf.int", conf_level = 0.99)

modelsummary(models, statistic = c(
  "t = {statistic}",
  "se = {std.error}",
  "conf.int"))

# estimate
modelsummary(models,
  statistic = NULL,
  estimate = "{estimate} [{conf.low}, {conf.high}]")

modelsummary(models,
  estimate = c(
    "{estimate}{stars}",
    "{estimate} ({std.error})"))

# vcov
modelsummary(models, vcov = "robust")

modelsummary(models, vcov = list("classical", "stata"))

modelsummary(models, vcov = sandwich::vcovHC)

modelsummary(models,
  vcov = list(stats::vcov, sandwich::vcovHC))

modelsummary(models,
  vcov = list(
    c("(Intercept)" = "", "Height" = "!"),
    c("(Intercept)" = "", "Height" = "!", "Volume" = "!!")))

# vcov with custom names
modelsummary(
  models,
  vcov = list(
    "Stata Corp" = "stata",
    "Newey Lewis & the News" = "NeweyWest"))

# fmt
mod <- lm(mpg ~ hp + drat + qsec, data = mtcars)

modelsummary(mod, fmt = 3)

modelsummary(mod, fmt = fmt_significant(3))

modelsummary(mod, fmt = NULL)

modelsummary(mod, fmt = fmt_decimal(4))

modelsummary(mod, fmt = fmt_sprintf("%.5f"))

modelsummary(mod, fmt = fmt_statistic(estimate = 4, conf.int = 1), statistic = "conf.int")

modelsummary(mod, fmt = fmt_term(hp = 4, drat = 1, default = 2))

m <- lm(mpg ~ I(hp * 1000) + drat, data = mtcars)
f <- function(x) format(x, digits = 3, nsmall = 2, scientific = FALSE, trim = TRUE)
modelsummary(m, fmt = f, gof_map = NA)

# coef_rename
modelsummary(models, coef_rename = c("Volume" = "Large", "Height" = "Tall"))

modelsummary(models, coef_rename = toupper)

modelsummary(models, coef_rename = coef_rename)

# coef_rename = TRUE for variable labels
datlab <- mtcars
datlab$cyl <- factor(datlab$cyl)
attr(datlab$hp, "label") <- "Horsepower"
attr(datlab$cyl, "label") <- "Cylinders"
modlab <- lm(mpg ~ hp * drat + cyl, data = datlab)
modelsummary(modlab, coef_rename = TRUE)

# coef_rename: unnamed vector of length equal to the number of terms in the final table
m <- lm(hp ~ mpg + factor(cyl), data = mtcars)
modelsummary(m, coef_omit = -(3:4), coef_rename = c("Cyl 6", "Cyl 8"))

# coef_map
modelsummary(models, coef_map = c("Volume" = "Large", "Height" = "Tall"))

modelsummary(models, coef_map = c("Volume", "Height"))

# coef_omit: omit the first and second coefficients
modelsummary(models, coef_omit = 1:2)

# coef_omit: omit coefficients matching one substring
modelsummary(models, coef_omit = "ei", gof_omit = ".*")

# coef_omit: omit a specific coefficient
modelsummary(models, coef_omit = "^Volume$", gof_omit = ".*")

# coef_omit: omit coefficients matching either one of two substring
# modelsummary(models, coef_omit = "ei|rc", gof_omit = ".*")

# coef_omit: keep coefficients starting with a substring (using a negative lookahead)
# modelsummary(models, coef_omit = "^(?!Vol)", gof_omit = ".*")

# coef_omit: keep coefficients matching a substring
modelsummary(models, coef_omit = "^(?!.*ei|.*pt)", gof_omit = ".*")

# shape: multinomial model
library(nnet)
multi <- multinom(factor(cyl) ~ mpg + hp, data = mtcars, trace = FALSE)

# shape: term names and group ids in rows, models in columns
modelsummary(multi, shape = response ~ model)

# shape: term names and group ids in rows in a single column
modelsummary(multi, shape = term:response ~ model)

# shape: term names in rows and group ids in columns
modelsummary(multi, shape = term ~ response:model)

# shape = "rcollapse"
panels <- list(
  "Panel A: MPG" = list(
    "A" = lm(mpg ~ hp, data = mtcars),
    "B" = lm(mpg ~ hp + factor(gear), data = mtcars)),
  "Panel B: Displacement" = list(
    "A" = lm(disp ~ hp, data = mtcars),
    "C" = lm(disp ~ hp + factor(gear), data = mtcars))
)

# shape = "cbind"
modelsummary(panels, shape = "cbind")

modelsummary(
  panels,
  shape = "rbind",
  gof_map = c("nobs", "r.squared"))

# title
modelsummary(models, title = "This is the title")

# title with LaTeX label (for numbering and referencing)
modelsummary(models, title = "This is the title \\label{tab:description}", escape = FALSE)

# add_rows
rows <- tibble::tribble(
  ~term, ~Bivariate, ~Multivariate,
  "Empty row", "-", "-",
  "Another empty row", "?", "?")
attr(rows, "position") <- c(1, 3)
modelsummary(models, add_rows = rows)

# notes
modelsummary(models, notes = list("A first note", "A second note"))

# gof_map: tribble
library(tibble)
gm <- tribble(
  ~raw, ~clean, ~fmt,
  "r.squared", "R Squared", 5)
modelsummary(models, gof_map = gm)

# gof_map: list of lists
f <- function(x) format(round(x, 3), big.mark = ",")
gm <- list(
  list("raw" = "nobs", "clean" = "N", "fmt" = f),
  list("raw" = "AIC", "clean" = "aic", "fmt" = f))
modelsummary(models, gof_map = gm)

# The `modelsummary` website includes \emph{many} examples and tutorials:
# https://modelsummary.com

library(modelsummary)

# load data and estimate models
utils::data(trees)
models <- list()
models[["Bivariate"]] <- lm(Girth ~ Height, data = trees)
models[["Multivariate"]] <- lm(Girth ~ Height + Volume, data = trees)

# simple table
modelsummary(models)

# statistic
modelsummary(models, statistic = NULL)

modelsummary(models, statistic = "p.value")

modelsummary(models, statistic = "statistic")

modelsummary(models, statistic = "conf.int", conf_level = 0.99)

modelsummary(models, statistic = c(
  "t = {statistic}",
  "se = {std.error}",
  "conf.int"))

# estimate
modelsummary(models,
  statistic = NULL,
  estimate = "{estimate} [{conf.low}, {conf.high}]")

modelsummary(models,
  estimate = c(
    "{estimate}{stars}",
    "{estimate} ({std.error})"))

# vcov
modelsummary(models, vcov = "robust")

modelsummary(models, vcov = list("classical", "stata"))

modelsummary(models, vcov = sandwich::vcovHC)

modelsummary(models,
  vcov = list(stats::vcov, sandwich::vcovHC))

modelsummary(models,
  vcov = list(
    c("(Intercept)" = "", "Height" = "!"),
    c("(Intercept)" = "", "Height" = "!", "Volume" = "!!")))

# vcov with custom names
modelsummary(
  models,
  vcov = list(
    "Stata Corp" = "stata",
    "Newey Lewis & the News" = "NeweyWest"))

# fmt
mod <- lm(mpg ~ hp + drat + qsec, data = mtcars)

modelsummary(mod, fmt = 3)

modelsummary(mod, fmt = fmt_significant(3))

modelsummary(mod, fmt = NULL)

modelsummary(mod, fmt = fmt_decimal(4))

modelsummary(mod, fmt = fmt_sprintf("%.5f"))

modelsummary(mod, fmt = fmt_statistic(estimate = 4, conf.int = 1), statistic = "conf.int")

modelsummary(mod, fmt = fmt_term(hp = 4, drat = 1, default = 2))

m <- lm(mpg ~ I(hp * 1000) + drat, data = mtcars)
f <- function(x) format(x, digits = 3, nsmall = 2, scientific = FALSE, trim = TRUE)
modelsummary(m, fmt = f, gof_map = NA)

# coef_rename
modelsummary(models, coef_rename = c("Volume" = "Large", "Height" = "Tall"))

modelsummary(models, coef_rename = toupper)

modelsummary(models, coef_rename = coef_rename)

# coef_rename = TRUE for variable labels
datlab <- mtcars
datlab$cyl <- factor(datlab$cyl)
attr(datlab$hp, "label") <- "Horsepower"
attr(datlab$cyl, "label") <- "Cylinders"
modlab <- lm(mpg ~ hp * drat + cyl, data = datlab)
modelsummary(modlab, coef_rename = TRUE)

# coef_rename: unnamed vector of length equal to the number of terms in the final table
m <- lm(hp ~ mpg + factor(cyl), data = mtcars)
modelsummary(m, coef_omit = -(3:4), coef_rename = c("Cyl 6", "Cyl 8"))

# coef_map
modelsummary(models, coef_map = c("Volume" = "Large", "Height" = "Tall"))

modelsummary(models, coef_map = c("Volume", "Height"))

# coef_omit: omit the first and second coefficients
modelsummary(models, coef_omit = 1:2)

# coef_omit: omit coefficients matching one substring
modelsummary(models, coef_omit = "ei", gof_omit = ".*")

# coef_omit: omit a specific coefficient
modelsummary(models, coef_omit = "^Volume$", gof_omit = ".*")

# coef_omit: omit coefficients matching either one of two substring
# modelsummary(models, coef_omit = "ei|rc", gof_omit = ".*")

# coef_omit: keep coefficients starting with a substring (using a negative lookahead)
# modelsummary(models, coef_omit = "^(?!Vol)", gof_omit = ".*")

# coef_omit: keep coefficients matching a substring
modelsummary(models, coef_omit = "^(?!.*ei|.*pt)", gof_omit = ".*")

# shape: multinomial model
library(nnet)
multi <- multinom(factor(cyl) ~ mpg + hp, data = mtcars, trace = FALSE)

# shape: term names and group ids in rows, models in columns
modelsummary(multi, shape = response ~ model)

# shape: term names and group ids in rows in a single column
modelsummary(multi, shape = term:response ~ model)

# shape: term names in rows and group ids in columns
modelsummary(multi, shape = term ~ response:model)

# shape = "rcollapse"
panels <- list(
  "Panel A: MPG" = list(
    "A" = lm(mpg ~ hp, data = mtcars),
    "B" = lm(mpg ~ hp + factor(gear), data = mtcars)),
  "Panel B: Displacement" = list(
    "A" = lm(disp ~ hp, data = mtcars),
    "C" = lm(disp ~ hp + factor(gear), data = mtcars))
)

# shape = "cbind"
modelsummary(panels, shape = "cbind")

modelsummary(
  panels,
  shape = "rbind",
  gof_map = c("nobs", "r.squared"))

# title
modelsummary(models, title = "This is the title")

# title with LaTeX label (for numbering and referencing)
modelsummary(models, title = "This is the title \\label{tab:description}", escape = FALSE)

# add_rows
rows <- tibble::tribble(
  ~term, ~Bivariate, ~Multivariate,
  "Empty row", "-", "-",
  "Another empty row", "?", "?")
attr(rows, "position") <- c(1, 3)
modelsummary(models, add_rows = rows)

# notes
modelsummary(models, notes = list("A first note", "A second note"))

# gof_map: tribble
library(tibble)
gm <- tribble(
  ~raw, ~clean, ~fmt,
  "r.squared", "R Squared", 5)
modelsummary(models, gof_map = gm)

# gof_map: list of lists
f <- function(x) format(round(x, 3), big.mark = ",")
gm <- list(
  list("raw" = "nobs", "clean" = "N", "fmt" = f),
  list("raw" = "AIC", "clean" = "aic", "fmt" = f))
modelsummary(models, gof_map = gm)

Update `modelsummary` and its dependencies

Description

Update modelsummary and its dependencies to the latest R-Universe or CRAN versions. The R session needs to be restarted after install.

Usage

update_modelsummary(source = "development")
update_modelsummary(source = "development")

Arguments

source

one of two strings: "development" or "cran"

Package 'modelsummary'

Help Index

Rename model terms

Description

Usage

Arguments

Examples

Persistent user settings for the modelsummary package

Description

Usage

Arguments

Summary tables using 2-sided formulae: crosstabs, frequencies, table 1s and more.

Description

Usage

Arguments

Details

Version 2.0.0, kableExtra, and tinytable

Global Options

Model labels: default column names

Table-making packages

Table themes

Model extraction functions

Formatting numeric entries

LaTeX preamble

Examples

References

Balance table: Summary statistics for different subsets of the data (e.g., control and treatment groups)

Description

Usage

Arguments

Version 2.0.0, kableExtra, and tinytable

Global Options

Model labels: default column names

Table-making packages

Table themes

Model extraction functions

Formatting numeric entries

LaTeX preamble

Examples

References

Generate a correlation table for all numeric variables in your dataset.

Description

Usage

Arguments

Version 2.0.0, kableExtra, and tinytable

Global Options

Model labels: default column names

Table-making packages

Table themes

Model extraction functions

Formatting numeric entries

LaTeX preamble

Examples

References

Format the content of a correlation table

Description

Usage

Arguments

Examples

Cross tabulations for categorical variables

Description

Usage

Arguments

Details

Version 2.0.0, kableExtra, and tinytable

Global Options

Model labels: default column names

Table-making packages

Table themes

Model extraction functions

Formatting numeric entries

LaTeX preamble

Examples

References

Draw a table from a data.frame

Description

Usage

Arguments

Version 2.0.0, kableExtra, and tinytable

References

Persistent user settings for the `modelsummary` package

Rounding with decimal digits in the `fmt` argument

Rounding with significant digits in the `fmt` argument

Rounding with the `sprintf()` function in the `fmt` argument

Rounding with decimal digits on a per-statistic basis in the `fmt` argument for `modelsummary()`

Rounding with decimal digits on a per-term basis in the `fmt` argument for `modelsummary()`