Desctable is a comprehensive descriptive and comparative tables generator for R.
Every person doing data analysis has to create tables for descriptive summaries of data (a.k.a. Table.1), or comparative tables.
Many packages, such as the aptly named tableone, address this issue. However, they often include hardcoded behaviors, have outputs not easily manipulable with standard R tools, or their syntax are outofstyle (e.g. the argument order makes them difficult to use with the pipe (%>%
)).
Enter desctable, a package built with the following objectives in mind:
desctable uses and exports the pipe (%>%
) operator (from packages magrittr and dplyr fame), though it is not mandatory to use it.
The single interface to the package is its eponymous desctable
function.
When used on a data.frame, it returns a descriptive table:
## N % Mean sd Med IQR
## 1 Sepal.Length 150 NA NA NA 5.80 1.3
## 2 Sepal.Width 150 NA 3.057333 0.4358663 3.00 0.5
## 3 Petal.Length 150 NA NA NA 4.35 3.5
## 4 Petal.Width 150 NA NA NA 1.30 1.5
## 5 Species 150 NA NA NA NA NA
## 6 Species: setosa 50 33.33333 NA NA NA NA
## 7 Species: versicolor 50 33.33333 NA NA NA NA
## 8 Species: virginica 50 33.33333 NA NA NA NA
## N Mean sd Med IQR
## 1 mpg 32 20.090625 6.0269481 19.200 7.37500
## 2 cyl 32 NA NA 6.000 4.00000
## 3 disp 32 NA NA 196.300 205.17500
## 4 hp 32 NA NA 123.000 83.50000
## 5 drat 32 3.596563 0.5346787 3.695 0.84000
## 6 wt 32 NA NA 3.325 1.02875
## 7 qsec 32 17.848750 1.7869432 17.710 2.00750
## 8 vs 32 NA NA 0.000 1.00000
## 9 am 32 NA NA 0.000 1.00000
## 10 gear 32 NA NA 4.000 1.00000
## 11 carb 32 NA NA 2.000 2.00000
As you can see with these two examples, desctable
describes every variable, with individual levels for factors. It picks statistical functions depending on the type and distribution of the variables in the data, and applies those statistical functions only on the relevant variables.
The object produced by desctable
is in fact a list of data.frames, with a “desctable” class.
Methods for reduction to a simple dataframe (as.data.frame
, automatically used for printing), conversion to markdown (pander
), and interactive html output with DT (datatable
) are provided:
N  %  Mean  sd  Med  IQR  

Sepal.Length  150  5.8  1.3  
Sepal.Width  150  3.1  0.44  3  0.5  
Petal.Length  150  4.3  3.5  
Petal.Width  150  1.3  1.5  
Species  150  
setosa  50  33  
versicolor  50  33  
virginica  50  33 
Calls to pander
and datatable
with “regular” dataframes will not be affected by the defaults used in the package, and you can modify these defaults for desctable objects.
Subsequent outputs in this vignette section will use DT. The datatable
wrapper function for desctable objects comes with some default options and formatting such as freezing the row names and table header, export buttons, and rounding of values. Both pander
and datatable
wrapper take a digits argument to set the number of decimals to show. (pander
uses the digits, justify and missing arguments of pandoc.table
, whereas datatable
calls prettyNum
with the digits
parameter, and removes NA
values. You can set digits = NULL
if you want the full table and format it yourself)
desctable
chooses statistical functions for you using this algorithm:
For each variable in the table, compute the relevant statistical functions in that list (nonapplicable functions will safely return NA
).
How does it work, and how can you adapt this behavior to your needs?
desctable
takes an optional stats argument. This argument can either be:
This is the default, using the stats_auto
function provided in the package.
Several other “automatic statistical functions” are defined in this package: stats_auto
, stats_default
, stats_normal
, stats_nonnormal
.
You can also provide your own automatic function, which needs to
Statistical functions can be any function defined in R that you want to use, such as length
or mean
.
The only condition is that they return a single numerical value. One exception is when they return a vector of length 1 + nlevels(x)
when applied to factors, as is needed for the percent
function.
As mentioned above, they need to be used inside a named list, such as
The names will be used as column headers in the resulting table, and the functions will be applied safely on the variables (errors return NA
, and for factors the function will be used on individual levels).
Several convenience functions are included in this package. For statistical function we have: percent
, which prints percentages of levels in a factor, and IQR
which reimplements stats::IQR
but works better with NA
values.
Be aware that all functions will be used on variables stripped of their NA
values!
This is necessary for most statistical functions to be useful, and makes N (length
) show only the number of observations in the dataset for each variable.
The general form of these formulas is
A predicate function is any function returning either TRUE
or FALSE
when applied on a vector, such as is.factor
, is.numeric
, and is.logical
.
desctable provides the is.normal
function to test for normality (it is equivalent to length(na.omit(x)) > 30 & shapiro.test(x)$p.value > .1
).
The FALSE option can be omitted and NA
will be produced if the condition in the predicate is not met.
These statements can be nested using parentheses.
For example:
is.factor ~ percent  (is.normal ~ mean)
will either use percent
if the variable is a factor, or mean
if and only if the variable is normally distributed.
You can mix “bare” statistical functions and formulas in the list defining the statistics you want to use in your table.
iris %>%
desctable(stats = list("N" = length,
"%/Mean" = is.factor ~ percent  (is.normal ~ mean),
"Median" = is.normal ~ NA  median)) %>%
datatable()
For reference, here is the body of the stats_auto
function in the package:
## function (data)
## {
## shapiro < data %>% Filter(f = is.numeric) %>% lapply(is.normal) %>%
## unlist()
## if (length(shapiro) == 0) {
## normal < F
## nonnormal < F
## }
## else {
## normal < any(shapiro)
## nonnormal < any(!shapiro)
## }
## fact < any(data %>% lapply(is.factor) %>% unlist())
## if (fact & normal & !nonnormal)
## stats_normal(data)
## else if (fact & !normal & nonnormal)
## stats_nonnormal(data)
## else if (fact & !normal & !nonnormal)
## list(N = length, `%` = percent)
## else if (!fact & normal & nonnormal)
## list(N = length, Mean = is.normal ~ mean, sd = is.normal ~
## sd, Med = stats::median, IQR = is.factor ~ NA  IQR)
## else if (!fact & normal & !nonnormal)
## list(N = length, Mean = mean, sd = stats::sd)
## else if (!fact & !normal & nonnormal)
## list(N = length, Med = stats::median, IQR = IQR)
## else stats_default(data)
## }
## <bytecode: 0x560645472070>
## <environment: namespace:desctable>
It is often the case that variable names are not “pretty” enough to be used asis in a table.
Although you could still edit the variable labels in the table afterwards using subsetting or string replacement functions, it is possible to mention a labels argument.
The labels argument is a named character vector associating variable names and labels.
You don’t need to provide labels for all the variables, and extra labels will be silently discarded. This allows you to define a “global” labels vector and use it for every table even after variable selections.
mtlabels < c(mpg = "Miles/(US) gallon",
cyl = "Number of cylinders",
disp = "Displacement (cu.in.)",
hp = "Gross horsepower",
drat = "Rear axle ratio",
wt = "Weight (1000 lbs)",
qsec = "¼ mile time",
vs = "V/S",
am = "Transmission",
gear = "Number of forward gears",
carb = "Number of carburetors")
mtcars %>%
dplyr::mutate(am = factor(am, labels = c("Automatic", "Manual"))) %>%
desctable(labels = mtlabels) %>%
datatable()
Creating a comparative table (between groups defined by a factor) using desctable
is as easy as creating a descriptive table.
It uses the well known group_by
function from dplyr:
## Species: setosa (n=50) / N Species: setosa (n=50) / Mean
## 1 Sepal.Length 50 5.006
## 2 Sepal.Width 50 3.428
## 3 Petal.Length 50 NA
## 4 Petal.Width 50 NA
## Species: setosa (n=50) / sd Species: setosa (n=50) / Med
## 1 0.3524897 5.0
## 2 0.3790644 3.4
## 3 NA 1.5
## 4 NA 0.2
## Species: setosa (n=50) / IQR Species: versicolor (n=50) / N1
## 1 0.400 50
## 2 0.475 50
## 3 0.175 50
## 4 0.100 50
## Species: versicolor (n=50) / Mean1 Species: versicolor (n=50) / sd1
## 1 5.936 0.5161711
## 2 2.770 0.3137983
## 3 4.260 0.4699110
## 4 NA NA
## Species: versicolor (n=50) / Med1 Species: versicolor (n=50) / IQR1
## 1 5.90 0.700
## 2 2.80 0.475
## 3 4.35 0.600
## 4 1.30 0.300
## Species: virginica (n=50) / N2 Species: virginica (n=50) / Mean2
## 1 50 6.588
## 2 50 2.974
## 3 50 5.552
## 4 50 NA
## Species: virginica (n=50) / sd2 Species: virginica (n=50) / Med2
## 1 0.6358796 6.50
## 2 0.3224966 3.00
## 3 0.5518947 5.55
## 4 NA 2.00
## Species: virginica (n=50) / IQR2 tests / p
## 1 0.675 1.505059e28
## 2 0.375 4.492017e17
## 3 0.775 4.803974e29
## 4 0.500 3.261796e29
## tests / test
## 1 . %>% oneway.test(var.equal = F)
## 2 . %>% oneway.test(var.equal = T)
## 3 kruskal.test
## 4 kruskal.test
The result is a table containing a descriptive subtable for each level of the grouping factor (the statistical functions rules are applied to each subtable independently), with the statistical tests performed, and their p values.
When displayed as a flat dataframe, the grouping header appears in each variable.
You can also see the grouping headers by inspecting the resulting object, which is a deep list of dataframes, each dataframe named after the grouping factor and its levels (with sample size for each).
## List of 5
## $ Variables :'data.frame': 4 obs. of 1 variable:
## ..$ Variables: chr [1:4] "Sepal.Length" "Sepal.Width" "Petal.Length" "Petal.Width"
## $ Species: setosa (n=50) :'data.frame': 4 obs. of 5 variables:
## ..$ N : int [1:4] 50 50 50 50
## ..$ Mean: num [1:4] 5.01 3.43 NA NA
## ..$ sd : num [1:4] 0.352 0.379 NA NA
## ..$ Med : num [1:4] 5 3.4 1.5 0.2
## ..$ IQR : num [1:4] 0.4 0.475 0.175 0.1
## $ Species: versicolor (n=50):'data.frame': 4 obs. of 5 variables:
## ..$ N : int [1:4] 50 50 50 50
## ..$ Mean: num [1:4] 5.94 2.77 4.26 NA
## ..$ sd : num [1:4] 0.516 0.314 0.47 NA
## ..$ Med : num [1:4] 5.9 2.8 4.35 1.3
## ..$ IQR : num [1:4] 0.7 0.475 0.6 0.3
## $ Species: virginica (n=50) :'data.frame': 4 obs. of 5 variables:
## ..$ N : int [1:4] 50 50 50 50
## ..$ Mean: num [1:4] 6.59 2.97 5.55 NA
## ..$ sd : num [1:4] 0.636 0.322 0.552 NA
## ..$ Med : num [1:4] 6.5 3 5.55 2
## ..$ IQR : num [1:4] 0.675 0.375 0.775 0.5
## $ tests :'data.frame': 4 obs. of 2 variables:
## ..$ p : num [1:4] 1.51e28 4.49e17 4.80e29 3.26e29
## ..$ test: chr [1:4] ". %>% oneway.test(var.equal = F)" ". %>% oneway.test(var.equal = T)" "kruskal.test" "kruskal.test"
##  attr(*, "class")= chr "desctable"
You can specify groups based on any variable, not only factors:
cyl: 4 (n=11) N 
Med 
IQR 
cyl: 6 (n=7) N1 
Med1 
IQR1 
cyl: 8 (n=14) N2 
Med2 
IQR2 
tests p 
test 


mpg  11  26  7.6  7  20  2.4  14  15  1.8  2.6e06  kruskal.test 
disp  11  108  42  7  168  36  14  350  88  1.6e06  kruskal.test 
hp  11  91  30  7  110  13  14  192  65  3.3e06  kruskal.test 
drat  11  4.1  0.35  7  3.9  0.56  14  3.1  0.15  0.00075  kruskal.test 
wt  11  2.2  0.74  7  3.2  0.62  14  3.8  0.48  1.1e05  kruskal.test 
qsec  11  19  1.4  7  18  2.4  14  17  1.5  0.0062  kruskal.test 
vs  11  1  0  7  1  1  14  0  0  3.2e05  kruskal.test 
am  11  1  0.5  7  0  1  14  0  0  0.014  kruskal.test 
gear  11  4  0  7  4  0.5  14  3  0  0.0062  kruskal.test 
carb  11  2  1  7  4  1.5  14  3.5  1.8  0.0017  kruskal.test 
Also with conditions:
And even on multiple nested groups:
mtcars %>%
dplyr::mutate(am = factor(am, labels = c("Automatic", "Manual"))) %>%
group_by(vs, am, cyl) %>%
desctable() %>%
datatable()
In the case of nested groups (a.k.a. subgroup analysis), statistical tests are performed only between the groups of the deepest grouping level.
Statistical tests are automatically selected depending on the data and the grouping factor.
desctable
choses the statistical tests using the following algorithm:
fisher.test
no.test
(which does nothing)var.test
> .1) and normality of distribution in both groups, use t.test(var.equal = T)
var.test
< .1) but normality of distribution in both groups, use t.test(var.equal = F)
wilcox.test
bartlett.test
> .1) and normality of distribution in all groups, use oneway.test(var.equal = T)
bartlett.test
< .1) but normality of distribution in all groups, use oneway.test(var.equal = F)
kruskal.test
But what if you want to pick a specific test for a specific variable, or change all the tests altogether?
desctable
takes an optional tests argument. This argument can either be
This is the default, using the tests_auto
function provided in the package.
You can also provide your own automatic function, which needs to
This function will be used on every variable and every grouping factor to determine the appropriate test.
# Strictly equivalent to iris %>% group_by(Species) %>% desctable %>% datatable
iris %>%
group_by(Species) %>%
desctable(tests = tests_auto) %>%
datatable()
You can provide a named list of statistical functions, but here the mechanism is a bit different from the stats argument.
The list must contain either .auto
or .default
.
.auto
needs to be an automatic function, such as tests_auto
. It will be used by default on all variables to select a test.default
needs to be a singleterm formula containing a statistical test function that will be used on all variablesYou can also provide overrides to use specific tests for specific variables.
This is done using list items named as the variable and containing a singleterm formula function.
iris %>%
group_by(Petal.Length > 5) %>%
desctable(tests = list(.auto = tests_auto,
Species = ~chisq.test)) %>%
datatable()
mtcars %>%
dplyr::mutate(am = factor(am, labels = c("Automatic", "Manual"))) %>%
group_by(am) %>%
desctable(tests = list(.default = ~wilcox.test,
mpg = ~t.test)) %>%
datatable()
You might wonder why the formula expression. That is needed to capture the test name, and to provide it in the resulting table.
As with statistical functions, any statistical test function defined in R can be used.
The conditions are that the function
variable ~ grouping_variable
) as a first positional argument (as is the case with most tests, like t.test
), andp.value
element.Several convenience function are provided: formula versions for chisq.test
and fisher.test
using generic S3 methods (thus the behavior of standard calls to chisq.test
and fisher.test
are not modified), and ANOVA
, a partial application of oneway.test
with parameter var.equal = T.
In the stats argument, you can not only feed function names, but even arbitrary function definitions, functional sequences (a feature provided with the pipe (%>%
)), or partial applications (with the purrr package):
mtcars %>%
desctable(stats = list("N" = length,
"Sum of squares" = function(x) sum(x^2),
"Q1" = . %>% quantile(prob = .25),
"Q3" = purrr::partial(quantile, probs = .75))) %>%
datatable()
In the tests arguments, you can also provide function definitions, functional sequences, and partial applications in the formulas:
iris %>%
group_by(Species) %>%
desctable(tests = list(.auto = tests_auto,
Sepal.Width = ~function(f) oneway.test(f, var.equal = F),
Petal.Length = ~. %>% oneway.test(var.equal = T),
Sepal.Length = ~purrr::partial(oneway.test, var.equal = T))) %>%
datatable()
This allows you to modulate the behavior of desctable
in every detail, such as using paired tests, or non htest tests.
# This is a contrived example, which would be better solved with a dedicated function
library(survival)
bladder$surv < Surv(bladder$stop, bladder$event)
bladder %>%
group_by(rx) %>%
desctable(tests = list(.default = ~wilcox.test,
surv = ~. %>% survdiff %>% .$chisq %>% pchisq(1, lower.tail = F) %>% list(p.value = .))) %>%
datatable()