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. The package also ships with several shortcut summary functions: Min, Max, Mean, Median, Var, SD, NPercent, NUnique, Ncol, P0, P25, P50, P75, P100.

  output = "default",
  fmt = 2,
  title = NULL,
  notes = NULL,
  align = NULL,
  add_columns = NULL,
  add_rows = NULL,
  sparse_header = TRUE,
  escape = TRUE,



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.


A data.frame (or tibble)


filename or object type (character string)

  • Supported filename extensions: .html, .tex, .md, .txt, .png, .jpg.

  • Supported object types: "default", "html", "markdown", "latex", "latex_tabular", "data.frame", "modelsummary_list", "gt", "kableExtra", "huxtable", "flextable", "jupyter".

  • 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.

  • The default output formats and table-making packages can be modified with global options. See the 'Details' section.


determines how to format numeric values

  • integer: the number of digits to keep after the period format(round(x, fmt), nsmall=fmt)

  • character: passed to the sprintf function (e.g., '%.3f' keeps 3 digits with trailing zero). See ?sprintf

  • function: returns a formatted character string.

  • Note on LaTeX formatting: To ensure proper typography, all numeric entries are enclosed in the \num{} command from the siunitx LaTeX package by default. This behavior can be altered with global options. See the 'Details' section.




list or vector of notes to append to the bottom of the table.


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, S.

  • "l": left-aligned column

  • "c": centered column

  • "r": right-aligned column

  • "d": dot-aligned column. Only supported for LaTeX/PDF tables produced by kableExtra. These commands must appear in the LaTeX preamble (they are added automatically when compiling Rmarkdown documents to PDF):

    • \usepackage{booktabs}

    • \usepackage{siunitx}

    • \newcolumntype{d}{S[input-symbols = ()]}


a data.frame (or tibble) with the same number of rows as your main table.


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.


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.`


boolean TRUE escapes or substitutes LaTeX/HTML characters which could prevent the file from compiling/displaying. This setting does not affect captions or notes.


all other arguments are passed through to the table-making functions. This allows users to pass arguments directly to datasummary in order to affect the behavior of other functions behind the scenes, for instance:


Visit the 'modelsummary' website for more usage examples:

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: kableExtra, gt, html, rtf, and LaTeX. When saving tables to other formats, nested labels will be combined to a "flat" header.

Global Options

The behavior of modelsummary can be affected by setting global options:

  • modelsummary_factory_default

  • modelsummary_factory_latex

  • modelsummary_factory_html

  • modelsummary_factory_png

  • modelsummary_get

  • modelsummary_format_numeric_latex

  • modelsummary_format_numeric_html

Table-making packages

modelsummary supports 4 table-making packages: kableExtra, gt, flextable, and huxtable. Some of these packages have overlapping functionalities. For example, 3 of those packages can export to LaTeX. 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_latex = 'gt') options(modelsummary_factory_word = 'huxtable') options(modelsummary_factory_png = 'gt')

Model extraction functions

modelsummary can use two sets of packages to extract information from statistical models: broom and the easystats family (performance and parameters). By default, it uses broom first and easystats as a fallback if broom fails. You can change the order of priorities or include goodness-of-fit extracted by both packages by setting:

options(modelsummary_get = "broom") options(modelsummary_get = "easystats") 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")


if (FALSE) { # 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 = '') 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 = '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) }