Package ‘compareGroups’

January 29, 2024

Type Package
Title Descriptive Analysis by Groups
Version 4.8.0
Date 2024-01-27
Depends R (>= 3.5.0)
Imports survival, tools, HardyWeinberg, rmarkdown, knitr, kableExtra,
methods, chron, stats, writexl, flextable, officer
Suggests tcltk2, shiny, shinyBS, shinyjs, shinyjqui, shinythemes,
shinyWidgets, shinydashboardPlus, DT, readxl, haven
Maintainer Isaac Subirana <[email protected]>
Description Create data summaries for quality control, extensive reports for explor-
ing data, as well as publication-ready univariate or bivariate tables in several for-
mats (plain text, HTML,LaTeX, PDF, Word or Excel. Create figures to quickly visualise the dis-
tribution of your data (boxplots, barplots, normality-plots, etc.). Display statistics (mean, me-
dian, frequencies, incidences, etc.). Perform the appropriate tests (t-test, Analysis of vari-
ance, Kruskal-Wallis, Fisher, log-rank, ...) depending on the nature of the described vari-
able (normal, non-normal or qualitative). Summarize genetic data (Single Nucleotide Polymor-
phisms) data displaying Allele Frequencies and performing Hardy-Weinberg Equilib-
rium tests among other typical statistics and tests for these kind of data.
License GPL (>= 2)
URL https://isubirana.github.io/compareGroups/
LazyLoad yes
Encoding UTF-8
BuildVignettes true
VignetteBuilder knitr
RoxygenNote 7.2.0
NeedsCompilation no
Author Isaac Subirana [aut, cre] (<https://orcid.org/0000-0003-1676-0197>),
Joan Salvador [ctb]
Repository CRAN
Date/Publication 2024-01-29 13:50:13 UTC

1
2 compareGroups-package

R topics documented:
compareGroups-package . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2
cGroupsGUI . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3
cGroupsWUI . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4
compareGroups . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5
compareSNPs . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12
createTable . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14
descrTable . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19
export2csv . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24
export2html . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 25
export2latex . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 26
export2md . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 28
export2pdf . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 31
export2word . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 33
export2xls . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 34
getResults . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 35
missingTable . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 36
padjustCompareGroups . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 38
printTable . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 39
radiograph . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 40
regicor . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 41
report . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 43
SNPs . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 44
strataTable . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 45
varinfo . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 46

Index 48

compareGroups-package Descriptive analysis by groups

Description
Create data summaries for quality control, extensive reports for exploring data, as well as publication-
ready univariate or bivariate tables in several formats (plain text, HTML,LaTeX, PDF, Word or
Excel). Display statistics (mean, median, frequencies, incidences, etc.). Create figures to quickly
visualise the distribution of your data (boxplots, barplots, normality-plots, etc.). Perform the appro-
priate tests (t-test, Analysis of variance, Kruskal-Wallis, Fisher, log-rank, ...) depending on the na-
ture of the described variable (normal, non-normal or qualitative). Summarize genetic data (Single
Nucleotide Polymorphisms) data displaying Allele Frequencies and performing Hardy-Weinberg
Equilibrium tests among other typical statistics and tests for these kind of data.
cGroupsGUI 3

Details

Package: compareGroups
Type: Package
Version: 4.8.0
Date: 2024-01-27
License: GPL version 2 or newer
LazyLoad: yes

Main functions: compareGroups, compareSNPs, createTable, descrTable, strataTable, missingTable,

export2latex, export2html, export2csv, export2pdf, export2md, export2word, export2xls,
report, radiograph, cGroupsGUI, cGroupsWUI

Author(s)
Main functions: Isaac Subirana <isubirana<at>imim.es>, Joan Vila <jvila<at>imim.es>, Héctor
Sanz <hsrodenas<at>gmail.com>, Gavin Lucas <gavin.lucas<at>cleargenetics.com> and David Giménez
<dgimenez1<at>imim.es>

Web User Interface: Isaac Subirana <isubirana<at>imim.es>, Judith Peñafiel <jpenafiel<at>imim.es>,

Gavin Lucas <gavin.lucas<at>cleargenetics.com> and David Giménez <dgimenez1<at>imim.es>

Maintainer: Isaac Subirana <isubirana<at>imim.es>

References
Isaac Subirana, Hector Sanz, Joan Vila (2014). Building Bivariate Tables: The compareGroups
Package for R. Journal of Statistical Software, 57(12), 1-16. URL https://www.jstatsoft.org/
v57/i12/.

cGroupsGUI Graphical user interface based on tcltk tools

Description
This function allows the user to build tables in an easy and intuitive way and to modify several
options, using a graphical interface.

Usage
cGroupsGUI(X)

Arguments
X a matrix or a data.frame. ’X’ must exist in .GlobalEnv.
4 cGroupsWUI

Details

See the vignette for more detailed examples illustrating the use of this function.

Note

If a data.frame or a matrix is passed through ’X’ argument or is loaded by the ’Load data’ GUI
menu, this object is placed in the .GlobalEnv. Manipulating this data.frame or matrix while GUI
is opened may produce an error in executing the GUI operations.

See Also

cGroupsWUI, compareGroups, createTable

Examples
## Not run:
data(regicor)
cGroupsGUI(regicor)

## End(Not run)

cGroupsWUI Web User Interface based on Shiny tools.

Description

This function opens a web browser with a graphical interface based on shiny package.

Usage

cGroupsWUI(port = 8102L)

Arguments

port integer. Same as ’port’ argument of runApp. Default value is 8102L.

Note

If an error occurs when launching the web browser, it may be solved by changing the port number.

See Also

cGroupsGUI, compareGroups, createTable

compareGroups 5

Examples

## Not run:

require(compareGroups)

cGroupsWUI()

## End(Not run)

compareGroups Descriptives by groups

Description
This function performs descriptives by groups for several variables. Depending on the nature of
these variables, different descriptive statistics are calculated (mean, median, frequencies or K-M
probabilities) and different tests are computed as appropriate (t-test, ANOVA, Kruskall-Wallis,
Fisher, log-rank, ...).

Usage
compareGroups(formula, data, subset, na.action = NULL, y = NULL, Xext = NULL,
selec = NA, method = 1, timemax = NA, alpha = 0.05, min.dis = 5, max.ylev = 5,
max.xlev = 10, include.label = TRUE, Q1 = 0.25, Q3 = 0.75, simplify = TRUE,
ref = 1, ref.no = NA, fact.ratio = 1, ref.y = 1, p.corrected = TRUE,
compute.ratio = TRUE, include.miss = FALSE, oddsratio.method = "midp",
chisq.test.perm = FALSE, byrow = FALSE, chisq.test.B = 2000, chisq.test.seed = NULL,
Date.format = "d-mon-Y", var.equal = TRUE, conf.level = 0.95, surv=FALSE,
riskratio = FALSE, riskratio.method = "wald", compute.prop = FALSE,
lab.missing = "'Missing'")
## S3 method for class 'compareGroups'
plot(x, file, type = "pdf", bivar = FALSE, z=1.5,
n.breaks = "Sturges", perc = FALSE, ...)

Arguments
formula an object of class "formula" (or one that can be coerced to that class). Right
side of ~ must have the terms in an additive way, and left side of ~ must contain
the name of the grouping variable or can be left in blank (in this latter case
descriptives for whole sample are calculated and no test is performed).
data an optional data frame, list or environment (or object coercible by ’as.data.frame’
to a data frame) containing the variables in the model. If they are not found in
’data’, the variables are taken from ’environment(formula)’.
6 compareGroups

subset an optional vector specifying a subset of individuals to be used in the computa-

tion process. It is applied to all row-variables. ’subset’ and ’selec’ are added in
the sense of ’&’ to be applied in every row-variable.
na.action a function which indicates what should happen when the data contain NAs. The
default is NULL, and that is equivalent to na.pass, which means no action.
Value na.exclude can be useful if it is desired to removed all individuals with
some NA in any variable.
y a vector variable that distinguishes the groups. It must be either a numeric,
character, factor or NULL. Default value is NULL which means that descriptives
for whole sample are calculated and no test is performed.
Xext a data.frame or a matrix with the same rows / individuals contained in X, and
maybe with different variables / columns than X. This argument is used by
compareGroups.default in the sense that the variables specified in the argu-
ment selec are searched in Xext and/or in the .GlobalEnv. If Xext is NULL,
then Xext is created from variables of X plus y. Default value is NULL.
selec a list with as many components as row-variables. If list length is 1 it is re-
cycled for all row-variables. Every component of ’selec’ is an expression that
will be evaluated to select the individuals to be analyzed for every row-variable.
Otherwise, a named list specifying ’selec’ row-variables is applied. ’.else’ is a
reserved name that defines the selection for the rest of the variables; if no ’.else’
variable is defined, default value is applied for the rest of the variables. Default
value is NA; all individuals are analyzed (no subsetting).
method integer vector with as many components as row-variables. If its length is 1 it is
recycled for all row-variables. It only applies for continuous row-variables (for
factor row-variables it is ignored). Possible values are: 1 - forces analysis as
"normal-distributed"; 2 - forces analysis as "continuous non-normal"; 3 - forces
analysis as "categorical"; and 4 - NA, which performs a Shapiro-Wilks test to
decide between normal or non-normal. Otherwise, a named vector specifying
’method’ row-variables is applied. ’.else’ is a reserved name that defines the
method for the rest of the variables; if no ’.else’ variable is defined, default
value is applied. Default value is 1.
timemax double vector with as many components as row-variables. If its length is 1 it
is recycled for all row-variables. It only applies for ’Surv’ class row-variables
(for all other row-variables it is ignored). This value indicates at which time
the K-M probability is to be computed. Otherwise, a named vector specifying
’timemax’ row-variables is applied. ’.else’ is a reserved name that defines the
’timemax’ for the rest of the variables; if no ’.else’ variable is defined, default
value is applied. Default value is NA; K-M probability is then computed at the
median of observed times.
alpha double between 0 and 1. Significance threshold for the shapiro.test normality
test for continuous row-variables. Default value is 0.05.
min.dis an integer. If a non-factor row-variable contains less than ’min.dis’ different
values and ’method’ argument is set to NA, then it will be converted to a factor.
Default value is 5.
max.ylev an integer indicating the maximum number of levels of grouping variable (’y’).
If ’y’ contains more than ’max.ylev’ levels, then the function ’compareGroups’
produces an error. Default value is 5.
compareGroups 7

max.xlev an integer indicating the maximum number of levels when the row-variable is a
factor. If the row-variable is a factor (or converted to a factor if it is a character,
for example) and contains more than ’max.xlev’ levels, then it is removed from
the analysis and a warning is printed. Default value is 10.
include.label logical, indicating whether or not variable labels have to be shown in the results.
Default value is TRUE
Q1 double between 0 and 1, indicating the quantile to be displayed as the first num-
ber inside the square brackets in the bivariate table. To compute the minimum
just type 0. Default value is 0.25 which means the first quartile.
Q3 double between 0 and 1, indicating the quantile to be displayed as the second
number inside the square brackets in the bivariate table. To compute the maxi-
mum just type 1. Default value is 0.75 which means the third quartile.
simplify logical, indicating whether levels with no values must be removed for grouping
variable and for row-variables. Default value is TRUE.
ref an integer vector with as many components as row-variables. If its length is 1 it
is recycled for all row-variables. It only applies for categorical row-variables. Or
a named vector specifying which row-variables ’ref’ is applied (a reserved name
is ’.else’ which defines the reference category for the rest of the variables); if no
’.else’ variable is defined, default value is applied for the rest of the variables.
Default value is 1.
ref.no character specifying the name of the level to be the reference for Odds Ratio
or Hazard Ratio. It is not case-sensitive. This is especially useful for yes/no
variables. Default value is NA which means that category specified in ’ref’ is
the one selected to be the reference.
fact.ratio a double vector with as many components as row-variables indicating the units
for the HR / OR (note that it does not affect the descriptives). If its length
is 1 it is recycled for all row-variables. Otherwise, a named vector specifying
’fact.ratio’ row-variables is applied. ’.else’ is a reserved name that defines the
reference category for the rest of the variables; if no ’.else’ variable is defined,
default value is applied. Default value is 1.
ref.y an integer indicating the reference category of y variable for computing the OR,
when y is a binary factor. Default value is 1.
p.corrected logical, indicating whether p-values for pairwise comparisons must be corrected.
It only applies when there is a grouping variable with more than 2 categories.
Default value is TRUE.
compute.ratio logical, indicating whether Odds Ratio (for a binary response) or Hazard Ratio
(for a time-to-event response) must be computed. Default value is TRUE.
include.miss logical, indicating whether to treat missing values as a new category for categor-
ical variables. Default value is FALSE.
oddsratio.method
Which method to compute the Odds Ratio. See ’method’ argument from oddsratio
(epitools package). Default value is "midp".
byrow logical or NA. Percentage of categorical variables must be reported by rows
(TRUE), by columns (FALSE) or by columns and rows to sum up 1 (NA). De-
fault value is FALSE, which means that percentages are reported by columns
(withing groups).
8 compareGroups

chisq.test.perm
logical. It applies a permutation chi squared test (chisq.test) instead of an
exact Fisher test (fisher.test). It only applies when expected count in some
cells are lower than 5.
chisq.test.B integer. Number of permutation when computing permuted chi squared test for
categorical variables. Default value is 2000.
chisq.test.seed
integer or NULL. Seed when performing permuted chi squared test for categor-
ical variables. Default value is NULL which sets no seed. It is important to
introduce some number different from NULL in order to reproduce the results
when permuted chi-squared test is performed.
Date.format character indicating how the dates are shown. Default is "d-mon-Y". See chron
for more details.
var.equal logical, indicating whether to consider equal variances when comparing means
on normal distributed variables on more than two groups. If TRUE anova func-
tion is applied and oneway.test otherwise. Default value is TRUE.
conf.level double. Conficende level of confidence interval for means, medians, proportions
or incidence, and hazard, odds and risk ratios. Default value is 0.95.
surv logical. Compute survival (TRUE) or incidence (FALSE) for time-to-event row-
variables. Default value is FALSE.
riskratio logical. Whether to compute Odds Ratio (FALSE) or Risk Ratio (TRUE). De-
fault value is FALSE.
riskratio.method
Which method to compute the Odds Ratio. See ’method’ argument from riskratio
(epitools package). Default value is "wald".
compute.prop logical. Compute proportions (TRUE) or percentages (FALSE) for cathegorical
row-variables. Default value is FALSE.
lab.missing character. Label for missing cathegory. Only applied when include.missing
= TRUE. Default value is ’Missing’.
Arguments passed to plot method.

x an object of class ’compareGroups’.

file a character string giving the name of the file. A bmp, jpg, png or tif file is
saved with an appendix added to ’file’ corresponding to the row-variable name.
If ’onefile’ argument is set to TRUE throught ’...’ argument of plot method
function, a unique PDF file is saved named as [file].pdf. If it is missing, multiple
devices are opened, one for each row-variable of ’x’ object.
type a character string indicating the file format where the plots are stored. Possibles
foramts are ’bmp’, ’jpg’, ’png’, ’tif’ and ’pdf’.Default value is ’pdf’.
bivar logical. If bivar=TRUE, it plots a boxplot or a barplot (for a continuous or
categorical row-variable, respectively) stratified by groups. If bivar=FALSE, it
plots a normality plot (for continuous row-variables) or a barplot (for categorical
row-variables). Default value is FALSE.
z double. Indicates threshold limits to be placed in the deviation from normality
plot. It is considered that too many points beyond this threshold indicates that
current variable is far to be normal-distributed. Default value is 1.5.
compareGroups 9

n.breaks same as argument ’breaks’ of hist.

perc logical. Relative frequencies (in percentatges) instead of absolute frequencies
are displayed in barplots for categorical variable.
... For ’plot’ method, ’...’ arguments are passed to pdf, bmp, jpeg, png or tiff if
’type’ argument equals to ’pdf’, ’bmp’, ’jpg’, ’png’ or ’tif’, respectively.

Details
Depending whether the row-variable is considered as continuous normal-distributed (1), continuous
non-normal distributed (2) or categorical (3), the following descriptives and tests are performed:
1- mean, standard deviation and t-test or ANOVA
2- median, 1st and 3rd quartiles (by default), and Kruskall-Wallis test
3- or absolute and relative frequencies and chi-squared or exact Fisher test when the expected fre-
quencies is less than 5 in some cell
Also, a row-variable can be of class ’Surv’. Then the probability of ’event’ at a fixed time (set up
with ’timemax’ argument) is computed and a logrank test is performed.

When there are more than 2 groups, it also performs pairwise comparisons adjusting for multiple
testing (Tukey when row-variable is normal-distributed and Benjamini & Hochberg method other-
wise), and computes p-value for trend. The p-value for trend is computed from the Pearson test
when row-variable is normal and from the Spearman test when it is continuous non normal. If
row-variable is of class ’Surv’, the score test is computed from a Cox model where the grouping
variable is introduced as an integer variable predictor. If the row-variable is categorical, the p-value
for trend is computed from Mantel-Haenszel test of trend.
If there are two groups, the Odds Ratio or Risk Ratio is computed for each row-variable. While, if
the response is of class ’Surv’ (i.e. time to event) Hazard Ratios are computed. When x-variable is a
factor, the Odds Ratio and Risk Ratio are computed using oddsratio and riskratio, respectively,
from epitools package. While when x-variable is a continuous variable, the Odds Ratio and Risk
Ratio are computed under a logistic regression with a canonical link and the log link, respectively.

The p-values for Hazard Ratios are computed using the logrank or Wald test under a Cox propor-
tional hazard regression when row-variable is categorical or continuous, respectively.

See the vignette for more detailed examples illustrating the use of this function and the methods
used.

Value
An object of class ’compareGroups’.

’print’ returns a table sample size, overall p-values, type of variable (’categorical’, ’normal’, ’non-
normal’ or ’Surv’) and the subset of individuals selected.

’summary’ returns a much more detailed list. Every component of the list is the result for each
row-variable, showing frequencies, mean, standard deviations, quartiles or K-M probabilities as
appropriate. Also, it shows overall p-values as well as p-trends and pairwise p-values among the
10 compareGroups

groups.

’plot’ displays, for all the analyzed variables, normality plots (with the Shapiro-Wilks test), barplots
or Kaplan-Meier plots depending on whether the row-variable is continuous, categorical or time-to-
response, respectevily. Also, bivariate plots can be displayed with stratified by groups boxplots or
barplots, setting ’bivar’ argument to TRUE.

An update method for ’compareGroups’ objects has been implemented and works as usual to change
all the arguments of previous analysis.

A subset, ’[’, method has been implemented for ’compareGroups’ objects. The subsetting indexes
can be either integers (as usual), row-variables names or row-variable labels.

Combine by rows,’rbind’, method has been implemented for ’compareGroups’ objects. It is useful
to distinguish row-variable groups.

See examples for further illustration about all previous issues.

Note
By default, the labels of the variables (row-variables and grouping variable) are displayed in the re-
sulting tables. These labels are taken from the "label" attribute of each variable. And if this attribute
is NULL, then the name of the variable is displayed, instead. To label non-labeled variables, or to
change their labels, specify its "label" atribute directly.

There may be no equivalence between the intervals of the OR / HR and p-values. For example,
when the response variable is binary and the row-variable is continuous, p-value is based on Mann-
Whitney U test or t-test depending on whether row-variable is normal distributed or not, respec-
tively, while the confidence interval is build using the Wald method (log(OR) -/+ 1.96*se). Or when
the answer is of class ’Surv’, p-value is computed with the logrank test, while confidence intervals
are based on the Wald method (log(HR) -/+ 1.96*se). Finally, when the response is binary and the
row variable is categorical, the p-value is based on the chi-squared or Fisher test when appropri-
ate, while confidence intervals are constructed from the median-unbiased estimation method (see
oddsratio function from epitools package).

Subjects selection criteria specified in ’selec’ and ’subset’ arguments are combined using ’&’ to be
applied to every row-variable.

Through ’...’ argument of ’plot’ method, some parameters such as figure size, multiple figures in a
unique file (only for ’pdf’ files), resolution, etc. are controlled. For more information about which
arguments can be passed depending on the format type, see pdf, bmp, jpeg, png or tiff.

Since version 4.0, date variables are supported. For this kind of variables only method==2 is ap-
plied, i.e. non-parametric tests for continuous variables are applied. However, the descriptive statis-
tics (medians and quantiles) are displayed in date format instead of numeric format.
compareGroups 11

References
Isaac Subirana, Hector Sanz, Joan Vila (2014). Building Bivariate Tables: The compareGroups
Package for R. Journal of Statistical Software, 57(12), 1-16. URL https://www.jstatsoft.org/
v57/i12/.

See Also
createTable

Examples

require(compareGroups)
require(survival)

# load REGICOR data

data(regicor)

# compute a time-to-cardiovascular event variable

regicor$tcv <- with(regicor, Surv(tocv, as.integer(cv=='Yes')))
attr(regicor$tcv,"label")<-"Cardiovascular"

# compute a time-to-overall death variable

regicor$tdeath <- with(regicor, Surv(todeath, as.integer(death=='Yes')))
attr(regicor$tdeath,"label") <- "Mortality"

# descriptives by sex
res <- compareGroups(sex ~ .-id-tocv-cv-todeath-death, data = regicor)
res

# summary of each variable

summary(res)

# univariate plots of all row-variables

## Not run:
plot(res)

## End(Not run)

# plot of all row-variables by sex

## Not run:
plot(res, bivar = TRUE)

## End(Not run)

# update changing the response: time-to-cardiovascular event.

# note that time-to-death must be removed since it is not possible
# not compute descriptives of a 'Surv' class object by another 'Surv' class object.

## Not run:
update(res, tcv ~ . + sex - tdeath - tcv)
12 compareSNPs

## End(Not run)

compareSNPs Summarise genetic data by groups.

Description

This function provides an extensive summary range of your SNP data, allowing you to perform in-
depth quality control of your genotyping results, and to explore your data before analysis. Summary
measures include allele and genotype frequencies and counts, missingness rate, Hardy Weinberg
equilibrium and more in the whole data set or stratified by other variables, such as case-control
status. It can also test for differences in missingness between groups.

Usage

compareSNPs(formula, data, subset, na.action = NULL, sep = "", verbose = FALSE, ...)

Arguments

formula an object of class "formula" (or one that can be coerced to that class). The right
side of ~ must have the terms in an additive way, and these terms must refer
to variables in ’data’ must be of character or factor classes whose levels are
the genotypes with the alleles written in their levels (e.g. A/A, A/T and T/T).
The left side of ~ must contain the name of the grouping variable or can be left
blank (in this case, summary data are provided for the whole sample, and no
missingness test is performed).
data an optional data frame, list or environment (or object coercible by ’as.data.frame’
to a data frame) containing the variables in the model. If they are not found in
’data’, the variables are taken from ’environment(formula)’.
subset an optional vector specifying a subset of individuals to be used in the computa-
tion process (applied to all genetic variables).
na.action a function which indicates what should happen when the data contain NAs. The
default is NULL, and that is equivalent to na.pass, which means no action.
Value na.exclude can be useful if it is desired to removed all individuals with
some NA in any variable.
sep character string indicating the separator between alleles (e.g. when using A/A,
A/T and T/T genotype codification, ’sep’ should be set to ’/’. Default value is ”
indicating that genotypes are coded as AA, AT and TT.
verbose logical, print results from HWChisq function. Default value is FALSE.
... currently ignored.
compareSNPs 13

Value

An object of class ’compareSNPs’ which is a data.frame (when no groups are specified on the left
of the ’~’ in the ’formula’ argument) or a list of data.frames, otherwise. Each data.frame contains
the following fields:
- Ntotal: Total number of samples for which genotyping was attempted
- Ntyped: Number of genotypes called
- Typed.p: Percentage genotyped
- Miss.t: Number of missing genotypes
- Miss.p: Proportion of missing genotypes
- Minor: Minor Allele
- MAF: Minor allele frequency
- A1: Allele 1
- A2: Allele 2
- A1.ct: Count Allele 1
- A2.ct: Count Allele 2
- A1.p: Frequency of Allele 1
- A2.p: Frequency of Allele 2
- Hom1: Allele 1 Homozygote
- Het: Heterozygote
- Hom2: Allele 2 Homozygote
- Hom1.ct: Allele 1 Homozygote count
- Het.ct: Heterozygote Count
- Hom2.ct: Allele 2 Homozygote count
- Hom1.p: Frequency of Allele 1 Homozygote
- Het.p: Heterozygote frequency
- Hom2.p: Frequency of Allele 2 Homozygote
- HWE.p: Hardy-Weinberg equilibrium p-value
Additionaly, when analysis is stratified by groups, the last component consists of a data.frame con-
taining the p-values of missingness comparison among groups.

’print’ returns a ’nice’ format table for each group with the main results for each SNP (Ntotal,
Ntyped, Minor, MAF, A1, A2, HWE.p), and the missingness test when group is considered.

Note

It uses some functions taken from SNPassoc created by Juan Ram?n Gonz?lez et al.

Hardy-Weinberg equilibrium test is performed using the HWChisqMat

Author(s)

Gavin Lucas (gavin.lucas<at>cleargenetics.com)

Isaac Subirana (isubirana<at>imim.es)

14 createTable

See Also

createTable

Examples

require(compareGroups)

# load example data

data(SNPs)

# visualize first rows

head(SNPs)

# select casco and all SNPs

myDat <- SNPs[,c(2,6:40)]

# QC of three SNPs by groups of cases and controls

res<-compareSNPs(casco ~ .-casco, myDat)
res

# QC of three SNPs of the whole data set

res<-compareSNPs( ~ .-casco, myDat)
res

createTable Table of descriptives by groups: bivariate table

Description

This functions builds a "compact" and "nice" table with the descriptives by groups.

Usage

createTable(x, hide = NA, digits = NA, type = NA, show.p.overall = TRUE,

show.all, show.p.trend, show.p.mul = FALSE, show.n, show.ratio =
FALSE, show.descr = TRUE, show.ci = FALSE, hide.no = NA, digits.ratio = NA,
show.p.ratio = show.ratio, digits.p = 3, sd.type = 1, q.type = c(1, 1),
extra.labels = NA, all.last = FALSE, lab.ref = "Ref.")
## S3 method for class 'createTable'
print(x, which.table = "descr", nmax = TRUE, header.labels = c(), ...)
## S3 method for class 'createTable'
plot(x, ...)
createTable 15

Arguments
x an object of class ’compareGroups’
hide a vector (or a list) with integers or characters with as many components as row-
variables. If its length is 1 it is recycled for all row-variables. Each component
specifies which category (the literal name of the category if it is a character, or
the position if it is an integer) must be hidden and not shown. This argument
only applies to categorical row-variables, and for continuous row-variables it is
ignored. If NA, all categories are displayed. Or a named vector (or a named
list) specifying which row-variables ’hide’ is applied, and for the rest of row-
variables default value is applied. Default value is NA.
digits an integer vector with as many components as row-variables. If its length is
1 it is recycled for all row-variables. Each component specifies the number of
significant decimals to be displayed. Or a named vector specifying which row-
variables ’digits’ is applied (a reserved name is ’.else’ which defines ’digits’ for
the rest of the variables); if no ’.else’ variable is defined, default value is applied
for the rest of the variables. Default value is NA which puts the ’appropriate’
number of decimals (see vignette for further details).
type an integer that indicates whether absolute and/or relative frequencies are dis-
played: 1 - only relative frequencies; 2 or NA - absolute and relative frequencies
in brackets; 3 - only absolute frequencies.
show.p.overall logical indicating whether p-value of overall groups significance (’p.overall’ col-
umn) is displayed or not. Default value is TRUE.
show.all logical indicating whether the ’[ALL]’ column (all data without stratifying by
groups) is displayed or not. Default value is FALSE if grouping variable is
defined, and FALSE if there are no groups.
show.p.trend logical indicating whether p-trend is displayed or not. It is always FALSE when
there are less than 3 groups. If this argument is missing, there are more than 2
groups and the grouping variable is an ordered factor, then p-trend is displayed.
By default, p-trend is not displayed, and it is displayed when there are more than
2 groups and the grouping variable is of class ordered-factor.
show.p.mul logical indicating whether the pairwise (between groups) comparisons p-values
are displayed or not. It is always FALSE when there are less than 3 groups.
Default value is FALSE.
show.n logical indicating whether number of individuals analyzed for each row-variable
is displayed or not in the ’descr’ table. Default value is FALSE and it is TRUE
when there are no groups.
show.ratio logical indicating whether OR / HR is displayed or not. Default value is FALSE.
show.descr logical indicating whether descriptives (i.e. mean, proportions, ...) are dis-
played. Default value is TRUE.
show.ci logical indicating whether to show confidence intervals of means, medians, pro-
porcions or incidences are displayed. If so, they are displayed between squared
brackets. Default value is FALSE.
hide.no character specifying the name of the level to be hidden for all categorical vari-
ables with 2 categories. It is not case-sensitive. The result is one row for the
16 createTable

variable with only the name displayed and not the category. This is especially
useful for yes/no variables. It is ignored for the categorical row-variables with
’hide’ argument different from NA. Default value is NA which means that no
category is hidden.
digits.ratio The same as ’digits’ argument but applied for the Hazard Ratio or Odds Ratio.
show.p.ratio logical indicating whether p-values corresponding to each Hazard Ratio / Odds
Ratio are shown.
digits.p integer indicating the number of decimals displayed for all p-values. Default
value is 3.
sd.type an integer that indicates how standard deviation is shown: 1 - mean (SD), 2 -
mean ? SD.
q.type a vector with two integer components. The first component refers to the type
of brackets to be displayed for non-normal row-variables (1 - squared and 2 -
rounded), while the second refers to the percentile separator (1 - ’;’, 2 - ’,’ and 3
- ’-’. Default value is c(1, 1).
extra.labels character vector of 4 components corresponding to key legend to be appended to
normal, non-normal, categorical or survival row-variables labels. Default value
is NA which appends no extra key. If it is set to c("","","",""), "Mean (SD)",
"Median [25th; 75th]", "N (%)" and "Incidence at time=timemax" are appended
(see argument timemax from compareGroups function.
all.last logical. Descriptives of the whole sample is placed after the descriptives by
groups. Default value is FALSE which places the descriptives of whole cohort
at first.
lab.ref character. String shown for reference category. "Ref." as default value.
which.table character indicating which table is printed. Possible values are ’descr’, ’avail’ or
’both’ (partial matching allowed), printing descriptives by groups table, avail-
ability data table or both tables, respectively. Default value is ’descr’.
nmax logical, indicating whether to show the number of subjects with at least one valid
value across all row-variables. Default value is TRUE.
header.labels a character named vector with ’all’, ’p.overall’, ’p.trend’, ’ratio’, ’p.ratio’ and
’N’ components indicating the label for ’[ALL]’, ’p.overall’, ’p.trend’, ’ratio’,
’p.ratio’ and ’N’ (available data), respectively. Default is a zero length vector
which makes no changes, i.e. ’[ALL]’, ’p.overall’, ’p.trend’, ’ratio’, ’p.ratio’
and ’N’ labels appear for descriptives of entire cohort, global p-value, p-value
for trend, HR/OR and p-value of each HR/OR and available data, respectively.
... other arguments passed to print.default.

Value
An object of class ’createTable’, which contains a list of 2 matrix:

descr a character matrix of descriptives for all row-variables by groups and p-values
in a ’compact’ format
avail a character matrix indicating the number of available data for each group, the
type of variable (categorical, continuous-normal or continuous-non-normal) and
the individuals selection made (if non selection ’ALL’ is displayed).
createTable 17

’print’ prints these two tables in a ’nice’ format.

’summary’ prints the ’available’ info table (it is a short form of print(x, which.table = 'avail')).
’update’ modifies previous results from ’createTable’.
’plot’ see the method in compareGroups function.
subsetting, ’[’, can also be applied to ’createTable’ objects in the same way as ’compareGroups’
objects.
combine by rows, ’rbind’, method can be applied to ’createTable’ objects, but only if all ’cre-
ateTable’ objects have the same columns. It is useful to distinguish row-variable groups. The
resulting object is of class ’rbind.createTable’ and ’createTable’.
combine by columns, ’cbind’, method can be applied to ’createTable’ objects, but only if all ’cre-
ateTable’ objects have the same rows. It may be used when combining different tables referring
to different subsets of people (for example, men and women). The resulting object is of class
’cbind.createTable’ and ’createTable’ and has its own ’print’ method.
See the vignette for more details.

Note
The way to compute the ’N’ shown in the bivariate table header, controlled by ’nmax’ argument,
has been changed from previous versions (<1.3). In the older versions ’N’ was computed as the
maximum across the cells withing each column (group) from the ’available data’ table (’avail’).
The p-values corresponding to the OR of a two level row-variable may not me equal to its p.overall
p-value. This is because statistical tests are different: the option ’midp.exact’ (see oddsratio
from epitools package for more details) is taken in the first case and Chi-square or Fisher exact
test in the second. The same happens when OR for a continuous value is performed: the p-value
corresponding to this OR is computed form a logistic regression and therefore may differ from
the one computed using a Student-T test or Kruskall Wallis test. This discordance may also be
present when computing the p-value corresponding to a Hazard Ratio for a categorical two level
row-variable: a Wald test or a long-rank test are peformed.

References
Isaac Subirana, Hector Sanz, Joan Vila (2014). Building Bivariate Tables: The compareGroups
Package for R. Journal of Statistical Software, 57(12), 1-16. URL https://www.jstatsoft.org/
v57/i12/.

See Also
compareGroups, export2latex, export2csv, export2html

Examples

require(compareGroups)
require(survival)

# load REGICOR data

data(regicor)
18 createTable

# compute a time-to-cardiovascular event variable

regicor$tcv <- with(regicor,Surv(tocv, as.integer(cv=='Yes')))
attr(regicor$tcv, "label")<-"Cardiovascular incidence"

# descriptives by time-to-cardiovascular event, taking 'no' category as

# the reference in computing HRs.
res <- compareGroups(tcv ~ age + sex + smoker + sbp + histhtn +
chol + txchol + bmi + phyact + pcs + tcv, regicor, ref.no='no')

# build table showing HR and hiding the 'no' category

restab <- createTable(res, show.ratio = TRUE, hide.no = 'no')
restab

# prints available info table

summary(restab)

# more...

## Not run:

# Adds the 'available data' column

update(restab, show.n=TRUE)

# Descriptive of the entire cohort

update(restab, x = update(res, ~ . ))

# .. changing the response variable to sex

# Odds Ratios (OR) are displayed instead of Hazard Ratios (HR).
# note that now it is possible to compute descriptives by time-to-death
# or time-to-cv but not the ORs .
# We set timemax to 5 years, to report the probability of death and CV at 5 years:
update(restab, x = update(res, sex ~ . - sex + tdeath + tcv, timemax = 5*365.25))

## Combining tables:

# a) By rows: takes the first four variables as a group and the rest as another group:
rbind("First group of variables"=restab[1:4],"Second group of variables"=
restab[5:length(res)])

# b) By columns: puts stratified tables by sex one beside the other:

res1<-compareGroups(year ~ . - id - sex, regicor)
restab1<-createTable(res1, hide.no = 'no')
restab2<-update(restab1, x = update(res1, subset = sex == 'Male'))
restab3<-update(restab1, x = update(res1, subset = sex == 'Female'))
cbind("ALL" = restab1, "MALES" = restab2, "FEMALES" = restab3)

## End(Not run)
descrTable 19

descrTable Perform descriptives and build the bivariate table.

Description
This functions builds a bivariate table calling compareGroups and createTable function in one step.

Usage
descrTable(formula, data, subset, na.action = NULL, y = NULL, Xext = NULL,
selec = NA, method = 1, timemax = NA, alpha = 0.05, min.dis = 5, max.ylev = 5,
max.xlev = 10, include.label = TRUE, Q1 = 0.25, Q3 = 0.75, simplify = TRUE,
ref = 1, ref.no = NA, fact.ratio = 1, ref.y = 1, p.corrected = TRUE,
compute.ratio = TRUE, include.miss = FALSE, oddsratio.method = "midp",
chisq.test.perm = FALSE, byrow = FALSE, chisq.test.B = 2000, chisq.test.seed = NULL,
Date.format = "d-mon-Y", var.equal = TRUE, conf.level = 0.95, surv = FALSE,
riskratio = FALSE, riskratio.method = "wald", compute.prop = FALSE,
lab.missing = "'Missing'",
hide = NA, digits = NA, type = NA, show.p.overall = TRUE,
show.all, show.p.trend, show.p.mul = FALSE, show.n, show.ratio =
FALSE, show.descr = TRUE, show.ci = FALSE, hide.no = NA, digits.ratio = NA,
show.p.ratio = show.ratio, digits.p = 3, sd.type = 1, q.type = c(1, 1),
extra.labels = NA, all.last = FALSE, lab.ref="Ref.")

Arguments
Arguments from compareGroups function:

formula an object of class "formula" (or one that can be coerced to that class). Right
side of ~ must have the terms in an additive way, and left side of ~ must contain
the name of the grouping variable or can be left in blank (in this latter case
descriptives for whole sample are calculated and no test is performed).
data an optional data frame, list or environment (or object coercible by ’as.data.frame’
to a data frame) containing the variables in the model. If they are not found in
’data’, the variables are taken from ’environment(formula)’.
subset an optional vector specifying a subset of individuals to be used in the computa-
tion process. It is applied to all row-variables. ’subset’ and ’selec’ are added in
the sense of ’&’ to be applied in every row-variable.
na.action a function which indicates what should happen when the data contain NAs. The
default is NULL, and that is equivalent to na.pass, which means no action.
Value na.exclude can be useful if it is desired to removed all individuals with
some NA in any variable.
y a vector variable that distinguishes the groups. It must be either a numeric,
character, factor or NULL. Default value is NULL which means that descriptives
for whole sample are calculated and no test is performed.
20 descrTable

Xext a data.frame or a matrix with the same rows / individuals contained in X, and
maybe with different variables / columns than X. This argument is used by
compareGroups.default in the sense that the variables specified in the argu-
ment selec are searched in Xext and/or in the .GlobalEnv. If Xext is NULL,
then Xext is created from variables of X plus y. Default value is NULL.
selec a list with as many components as row-variables. If list length is 1 it is re-
cycled for all row-variables. Every component of ’selec’ is an expression that
will be evaluated to select the individuals to be analyzed for every row-variable.
Otherwise, a named list specifying ’selec’ row-variables is applied. ’.else’ is a
reserved name that defines the selection for the rest of the variables; if no ’.else’
variable is defined, default value is applied for the rest of the variables. Default
value is NA; all individuals are analyzed (no subsetting).
method integer vector with as many components as row-variables. If its length is 1 it is
recycled for all row-variables. It only applies for continuous row-variables (for
factor row-variables it is ignored). Possible values are: 1 - forces analysis as
"normal-distributed"; 2 - forces analysis as "continuous non-normal"; 3 - forces
analysis as "categorical"; and 4 - NA, which performs a Shapiro-Wilks test to
decide between normal or non-normal. Otherwise, a named vector specifying
’method’ row-variables is applied. ’.else’ is a reserved name that defines the
method for the rest of the variables; if no ’.else’ variable is defined, default
value is applied. Default value is 1.
timemax double vector with as many components as row-variables. If its length is 1 it
is recycled for all row-variables. It only applies for ’Surv’ class row-variables
(for all other row-variables it is ignored). This value indicates at which time
the K-M probability is to be computed. Otherwise, a named vector specifying
’timemax’ row-variables is applied. ’.else’ is a reserved name that defines the
’timemax’ for the rest of the variables; if no ’.else’ variable is defined, default
value is applied. Default value is NA; K-M probability is then computed at the
median of observed times.
alpha double between 0 and 1. Significance threshold for the shapiro.test normality
test for continuous row-variables. Default value is 0.05.
min.dis an integer. If a non-factor row-variable contains less than ’min.dis’ different
values and ’method’ argument is set to NA, then it will be converted to a factor.
Default value is 5.
max.ylev an integer indicating the maximum number of levels of grouping variable (’y’).
If ’y’ contains more than ’max.ylev’ levels, then the function ’compareGroups’
produces an error. Default value is 5.
max.xlev an integer indicating the maximum number of levels when the row-variable is a
factor. If the row-variable is a factor (or converted to a factor if it is a character,
for example) and contains more than ’max.xlev’ levels, then it is removed from
the analysis and a warning is printed. Default value is 10.
include.label logical, indicating whether or not variable labels have to be shown in the results.
Default value is TRUE
Q1 double between 0 and 1, indicating the quantile to be displayed as the first num-
ber inside the square brackets in the bivariate table. To compute the minimum
just type 0. Default value is 0.25 which means the first quartile.
descrTable 21

Q3 double between 0 and 1, indicating the quantile to be displayed as the second

number inside the square brackets in the bivariate table. To compute the maxi-
mum just type 1. Default value is 0.75 which means the third quartile.
simplify logical, indicating whether levels with no values must be removed for grouping
variable and for row-variables. Default value is TRUE.
ref an integer vector with as many components as row-variables. If its length is 1 it
is recycled for all row-variables. It only applies for categorical row-variables. Or
a named vector specifying which row-variables ’ref’ is applied (a reserved name
is ’.else’ which defines the reference category for the rest of the variables); if no
’.else’ variable is defined, default value is applied for the rest of the variables.
Default value is 1.
ref.no character specifying the name of the level to be the reference for Odds Ratio
or Hazard Ratio. It is not case-sensitive. This is especially useful for yes/no
variables. Default value is NA which means that category specified in ’ref’ is
the one selected to be the reference.
fact.ratio a double vector with as many components as row-variables indicating the units
for the HR / OR (note that it does not affect the descriptives). If its length
is 1 it is recycled for all row-variables. Otherwise, a named vector specifying
’fact.ratio’ row-variables is applied. ’.else’ is a reserved name that defines the
reference category for the rest of the variables; if no ’.else’ variable is defined,
default value is applied. Default value is 1.
ref.y an integer indicating the reference category of y variable for computing the OR,
when y is a binary factor. Default value is 1.
p.corrected logical, indicating whether p-values for pairwise comparisons must be corrected.
It only applies when there is a grouping variable with more than 2 categories.
Default value is TRUE.
compute.ratio logical, indicating whether Odds Ratio (for a binary response) or Hazard Ratio
(for a time-to-event response) must be computed. Default value is TRUE.
include.miss logical, indicating whether to treat missing values as a new category for categor-
ical variables. Default value is FALSE.
oddsratio.method
Which method to compute the Odds Ratio. See ’method’ argument from oddsratio
(epitools package). Default value is "midp".
byrow logical or NA. Percentage of categorical variables must be reported by rows
(TRUE), by columns (FALSE) or by columns and rows to sum up 1 (NA). De-
fault value is FALSE, which means that percentages are reported by columns
(withing groups).
chisq.test.perm
logical. It applies a permutation chi squared test (chisq.test) instead of an
exact Fisher test (fisher.test). It only applies when expected count in some
cells are lower than 5.
chisq.test.B integer. Number of permutation when computing permuted chi squared test for
categorical variables. Default value is 2000.
chisq.test.seed
integer or NULL. Seed when performing permuted chi squared test for categor-
ical variables. Default value is NULL which sets no seed. It is important to
22 descrTable

introduce some number different from NULL in order to reproduce the results
when permuted chi-squared test is performed.
Date.format character indicating how the dates are shown. Default is "d-mon-Y". See chron
for more details.
var.equal logical, indicating whether to consider equal variances when comparing means
on normal distributed variables on more than two groups. If TRUE anova func-
tion is applied and oneway.test otherwise. Default value is TRUE.
conf.level double. Conficende level of confidence interval for means, medians, proportions
or incidence, and hazard, odds and risk ratios. Default value is 0.95.
surv logical. Compute survival (TRUE) or incidence (FALSE) for time-to-event row-
variables. Default value is FALSE.
riskratio logical. Whether to compute Odds Ratio (FALSE) or Risk Ratio (TRUE). De-
fault value is FALSE.
riskratio.method
Which method to compute the Odds Ratio. See ’method’ argument from riskratio
(epitools package). Default value is "wald".
compute.prop logical. Compute proportions (TRUE) or percentages (FALSE) for cathegorical
row-variables. Default value is FALSE.
lab.missing character. Label for missing cathegory. Only applied when include.missing
= TRUE. Default value is ’Missing’.

Arguments from createTable function:

hide a vector (or a list) with integers or characters with as many components as row-
variables. If its length is 1 it is recycled for all row-variables. Each component
specifies which category (the literal name of the category if it is a character, or
the position if it is an integer) must be hidden and not shown. This argument
only applies to categorical row-variables, and for continuous row-variables it is
ignored. If NA, all categories are displayed. Or a named vector (or a named
list) specifying which row-variables ’hide’ is applied, and for the rest of row-
variables default value is applied. Default value is NA.
digits an integer vector with as many components as row-variables. If its length is
1 it is recycled for all row-variables. Each component specifies the number of
significant decimals to be displayed. Or a named vector specifying which row-
variables ’digits’ is applied (a reserved name is ’.else’ which defines ’digits’ for
the rest of the variables); if no ’.else’ variable is defined, default value is applied
for the rest of the variables. Default value is NA which puts the ’appropriate’
number of decimals (see vignette for further details).
type an integer that indicates whether absolute and/or relative frequencies are dis-
played: 1 - only relative frequencies; 2 or NA - absolute and relative frequencies
in brackets; 3 - only absolute frequencies.
show.p.overall logical indicating whether p-value of overall groups significance (’p.overall’ col-
umn) is displayed or not. Default value is TRUE.
show.all logical indicating whether the ’[ALL]’ column (all data without stratifying by
groups) is displayed or not. Default value is FALSE if grouping variable is
defined, and FALSE if there are no groups.
descrTable 23

show.p.trend logical indicating whether p-trend is displayed or not. It is always FALSE when
there are less than 3 groups. If this argument is missing, there are more than 2
groups and the grouping variable is an ordered factor, then p-trend is displayed.
By default, p-trend is not displayed, and it is displayed when there are more than
2 groups and the grouping variable is of class ordered-factor.
show.p.mul logical indicating whether the pairwise (between groups) comparisons p-values
are displayed or not. It is always FALSE when there are less than 3 groups.
Default value is FALSE.
show.n logical indicating whether number of individuals analyzed for each row-variable
is displayed or not in the ’descr’ table. Default value is FALSE and it is TRUE
when there are no groups.
show.ratio logical indicating whether OR / HR is displayed or not. Default value is FALSE.
show.descr logical indicating whether descriptives (i.e. mean, proportions, ...) are dis-
played. Default value is TRUE.
show.ci logical indicating whether to show confidence intervals of means, medians, pro-
porcions or incidences are displayed. If so, they are displayed between squared
brackets. Default value is FALSE.
hide.no character specifying the name of the level to be hidden for all categorical vari-
ables with 2 categories. It is not case-sensitive. The result is one row for the
variable with only the name displayed and not the category. This is especially
useful for yes/no variables. It is ignored for the categorical row-variables with
’hide’ argument different from NA. Default value is NA which means that no
category is hidden.
digits.ratio The same as ’digits’ argument but applied for the Hazard Ratio or Odds Ratio.
show.p.ratio logical indicating whether p-values corresponding to each Hazard Ratio / Odds
Ratio are shown.
digits.p integer indicating the number of decimals displayed for all p-values. Default
value is 3.
sd.type an integer that indicates how standard deviation is shown: 1 - mean (SD), 2 -
mean ? SD.
q.type a vector with two integer components. The first component refers to the type
of brackets to be displayed for non-normal row-variables (1 - squared and 2 -
rounded), while the second refers to the percentile separator (1 - ’;’, 2 - ’,’ and 3
- ’-’. Default value is c(1, 1).
extra.labels character vector of 4 components corresponding to key legend to be appended to
normal, non-normal, categorical or survival row-variables labels. Default value
is NA which appends no extra key. If it is set to c("","","",""), "Mean (SD)",
"Median [25th; 75th]", "N (%)" and "Incidence at time=timemax" are appended
(see argument timemax from compareGroups function.
all.last logical. Descriptives of the whole sample is placed after the descriptives by
groups. Default value is FALSE which places the descriptives of whole cohort
at first.
lab.ref character. String shown for reference category. "Ref." as default value.
24 export2csv

Value
An object of class ’createTable’ (see createTable).
So, all methods implemented for createTable class objects can be applied (such as plot, ’[’, etc.).

Note
The use of descrTable function makes easier to build the table (it only needs one line), it may be
preferable to build the descriptive table in two steps when computing descriptives and p-values takes
some time: first use compareGroups function to store the descriptives and p-values in an object, and
then apply createTable to the this object. The two steps strategy saves time since descriptives and
p-values are not recomputed every time it is desired to costumize the descriptive table (number of
digits, etc.).

References
Isaac Subirana, Hector Sanz, Joan Vila (2014). Building Bivariate Tables: The compareGroups
Package for R. Journal of Statistical Software, 57(12), 1-16. URL https://www.jstatsoft.org/
v57/i12/.

See Also
createTable, compareGroups, export2latex, export2csv, export2html

Examples

require(compareGroups)

# load REGICOR data

data(regicor)

# perform descriptives by year and build the table.

# note the use of arguments from compareGroups (formula and data set) and
# arguments from createTable (hide.no and show.p.mul)
descrTable(year ~ ., regicor, hide.no="no", show.p.mul=TRUE)

export2csv Exporting descriptives table to plain text (CSV) format

Description
This function takes the result of createTable and exports the tables to plain text (CSV) format.

Usage
export2csv(x, file, which.table="descr", sep=",", nmax = TRUE, header.labels = c(), ...)
export2html 25

Arguments
x an object of class ’createTable’.
file file where table in CSV format will be written. Also, another file with the ex-
tension ’_appendix’ is written with the available data table.
which.table character indicating which table is printed. Possible values are ’descr’, ’avail’ or
’both’ (partial matching allowed), exporting descriptives by groups table, avail-
able data table or both tables, respectively. Default value is ’descr’.
sep character. The variable separator, same as ’sep’ argument from write.table.
Default value is ’,’.
nmax logical, indicating whether to show the number of subjects with at least one valid
value across all row-variables. Default value is TRUE.
header.labels see the ’header.labels’ argument from createTable.
... other arguments passed to write.table.

Note
The way to compute the ’N’ shown in the bivariate table header, controlled by ’nmax’ argument,
has been changed from previous versions (<1.3). In the older versions ’N’ was computed as the
maximum across the cells withing each column (group) from the ’available data’ table (’avail’).

See Also
createTable, export2latex, export2pdf, export2html, export2md, export2word

Examples

## Not run:
require(compareGroups)
data(regicor)
res <- compareGroups(sex ~. -id-todeath-death-tocv-cv, regicor)
export2csv(createTable(res, hide.no = 'n'), file=tempfile(fileext=".csv"))

## End(Not run)

export2html Exporting descriptives table to HTML format

Description
This function takes the result of createTable and exports the tables to HTML format.

Usage
export2html(x, file, which.table="descr", nmax = TRUE, header.labels = c(), ...)
26 export2latex

Arguments

x an object of class ’createTable’.

file file where table in HTML format will be written. Also, another file with the
extension ’_appendix’ is written with the available data table. If missing, the
HTML code is returned.
which.table character indicating which table is printed. Possible values are ’descr’, ’avail’ or
’both’ (partial matching allowed), exporting descriptives by groups table, avail-
ability data table or both tables, respectively. Default value is ’descr’.
nmax logical, indicating whether to show the number of subjects with at least one valid
value across all row-variables. Default value is TRUE.
header.labels see the ’header.labels’ argument from createTable.
... currently ignored.

Note

The way to compute the ’N’ shown in the bivariate table header, controlled by ’nmax’ argument,
has been changed from previous versions (<1.3). In the older versions ’N’ was computed as the
maximum across the cells withing each column (group) from the ’available data’ table (’avail’).

See Also

createTable, export2latex, export2pdf, export2csv, export2md, export2word

Examples

## Not run:
require(compareGroups)
data(regicor)
res <- compareGroups(sex ~. -id-todeath-death-tocv-cv, regicor)
export2html(createTable(res, hide.no = 'n'), file=tempfile(fileext=".html"))

## End(Not run)

export2latex Exporting descriptives table to LaTeX format

Description

This function takes the result of createTable and exports the tables to LaTeX format.
export2latex 27

Usage

export2latex(x, ...)
## S3 method for class 'createTable'
export2latex(x, file, which.table = 'descr', size = 'same',
nmax = TRUE, header.labels = c(), caption = NULL, loc.caption = 'top', label = NULL,
landscape = NA, colmax = 10, ...)
## S3 method for class 'cbind.createTable'
export2latex(x, file, which.table = 'descr', size = 'same',
nmax = TRUE, header.labels = c(), caption = NULL, loc.caption = 'top', label = NULL,
landscape = NA, colmax = 10, ...)

Arguments

x an object of class ’createTable’.

file Name of file where the resulting code should be saved. If file is missing, output
is displayed on screen. Also, another file with the extension ’_appendix’ is
written with the available data table.
which.table character indicating which table is exported. Possible values are ’descr’, ’avail’
or ’both’ (partial matching allowed), exporting descriptives by groups table,
availability data table or both tables, respectively. Default value is ’descr’.
size character indicating the size of the table elements. Possible values are: ’tiny’,
’scriptsize’, ’footnotesize’, ’small’, ’normalsize’, ’large’, ’Large’, ’LARGE’,’huge’,
’Huge’ or ’same’ (partial matching allowed). Default value is ’same’ which
means that font size of the table is the same as specified in the main LaTeX
document.
nmax logical, indicating whether to show the number of subjects with at least one valid
value across all row-variables. Default value is TRUE.
header.labels see the ’header.labels’ argument from createTable.
caption character specifying the table caption for descriptives and available data table. If
which.table=’both’ the first element of ’caption’ will be assigned to descriptives
table and the second to available data table. If it is set to "", no caption is
inserted. Default value is NULL, which writes ’Summary descriptives table by
groups of ’y” for descriptives table and ’Available data by groups of ’y” for the
available data table.
label character specifying the table label for descriptives and available data table.
This may be useful to cite the tables elsewhere in the LaTeX document. If
which.table=’both’ the first element of ’label’ will be assigned to descriptives
table and the second to available data table. Default value is NULL, which as-
signs no label to the table/s.
loc.caption character specifying the table caption location. Possible values are ’top’ or ’bot-
tom’ (partial matching allowed). Default value is ’top’.
landscape logical indicating whether the table must be placed in landscape, or NA that
places the table in landscape when there are more than ’colmax’ columns. De-
fault value is NA.
28 export2md

colmax integer indicating the maximum number of columns to make the table not to be
placed in landscape. This argument is only applied when ’landscape’ argument
is NA. Default value is 10.
... currently ignored.

Value
List of two possible components corresponding to the code of ’descr’ table and ’avail’ table. Each
component of the list is a character corresponding to the LaTeX code of these tables which can be
helpful for post-processing.

Note
The table is created in LaTeX language using the longtable environment. Therefore, it is necessary
to type \includepackage{longtable} in the preamble of the LaTeX main document where the
table code is inserted. Also, it it necessary to include the ’multirow’ LaTeX package. \
The way to compute the ’N’ shown in the bivariate table header, controlled by ’nmax’ argument,
has been changed from previous versions (<1.3). In the older versions ’N’ was computed as the
maximum across the cells withing each column (group) from the ’available data’ table (’avail’). \
When ’landscape’ argument is TRUE or there are more than ’colmax’ columns and ’landscape’ is
set to NA, LaTeX package ’lscape’ must be loaded in the tex document.

See Also
createTable, export2csv, export2html, export2pdf, export2md, export2word

Examples

## Not run:
require(compareGroups)
data(regicor)
res <- compareGroups(sex ~. -id-todeath-death-tocv-cv, regicor)
export2latex(createTable(res, hide.no = 'n'), file=tempfile(fileext=".tex"))

## End(Not run)

export2md Exporting descriptives table to Markdown format

Description
This function takes the result of createTable and exports the tables to markdown format. It may
be useful when inserting R code chunks in a Markdown file (.Rmd).
export2md 29

Usage
export2md(x, which.table = "descr", nmax = TRUE, header.labels = c(), caption = NULL,
format = "html", width = Inf, strip = FALSE, first.strip = FALSE,
background = "#D2D2D2", size = NULL, landscape=FALSE, header.background=NULL,
header.color=NULL, position="center",...)

Arguments
x an object of class ’createTable’.
which.table character indicating which table is printed. Possible values are ’descr’ or ’avail’(partial
matching allowed), exporting descriptives by groups table or availability data ta-
ble, respectively. Default value is ’descr’.
nmax logical, indicating whether to show the number of subjects with at least one valid
value across all row-variables. Default value is TRUE.
header.labels see the ’header.labels’ argument from createTable.
caption character specifying the table caption for descriptives and available data table. If
which.table=’both’ the first element of ’caption’ will be assigned to descriptives
table and the second to available data table. If it is set to "", no caption is
inserted. Default value is NULL, which writes ’Summary descriptives table by
groups of ’y” for descriptives table and ’Available data by groups of ’y” for the
available data table.
format character with three options: ’html’, ’latex’ or ’markdown’. If missing, it tries
to guess the default options of Rmarkdown file in which the table in inserted, or
html if it is not in a Rmarkdown file or format not specified.
width character string to specify the width of first column of descriptive table. It is
ignored when exporting to Word. Default value is Inf which makes the first
column to autoadjust to variable names. Other examples are ’10cm’, ’3in’ or
’30em’.
strip logical. It shadows table lines corresponding to each variable.
first.strip logical. It determines whether to shadow the first variable (TRUE) or the second
(FALSE). It only applies when strip argument is true.
background color code in HEX format for shadowed lines. You can use rgb function to
convert red, green and blue to HEX code. Default color is ’#D2D2D2’.
size numeric. Size of descriptive table. Default value is NULL which creates the
table in default size.
landscape logical. It determines whether to place the table in landscape (horizontal) format.
It only applies when format is ’latex’. Default value is FALSE.
header.background
color character for table header or ’NULL’. Default value is ’NULL’.
header.color color character for table header text. Default color is ’NULL’.
position character specifying the table location. Possible values are ’left’, ’center’, ’right’,
’float_left’ and ’float_right’. It only applies when compiling to HTML or PDF.
Default value is ’center’. See kable_styling position argument for more info.
... arguments passed to kable.
30 export2md

Value

It does not return anything, but the Markdown code to generate the descriptive or available table is
printed.

Note

The way to compute the ’N’ shown in the bivariate table header, controlled by ’nmax’ argument,
has been changed from previous versions (<1.3). In the older versions ’N’ was computed as the
maximum across the cells withing each column (group) from the ’available data’ table (’avail’).
Stratified tables, i.e. cbind.createTable class, are not supported when creating a Word document.

See Also

createTable, export2latex, export2pdf, export2csv, export2html, export2word

Examples

## Not run:

---
title: "Report"
output:
html_document: default
---

```{r setup, include=FALSE}

knitr::opts_chunk$set(echo = FALSE, warning=FALSE, message=FALSE)
```

```{r}
library(compareGroups)
data(regicor)
res <- compareGroups(year~., regicor)
restab <- createTable(res)
```

## Report section

The following table contains descriptives of **REGICOR** data

```{r}
export2md(restab, strip = TRUE, first.strip = TRUE)
```

## End(Not run)
export2pdf 31

export2pdf Exports tables to PDF files.

Description
This function creates automatically a PDF with the table. Also, the LaTeX code is stored in the
specified file.

Usage
export2pdf(x, file, which.table="descr", nmax=TRUE, header.labels=c(), caption=NULL,
width=Inf, strip=FALSE, first.strip=FALSE, background="#D2D2D2", size=NULL,
landscape=FALSE, numcompiled=2, header.background=NULL, header.color=NULL)

Arguments
x an object of class ’createTable’ or that inherits it.
file character specifying the PDF file resulting after compiling the LaTeX code cor-
responding to the table specified in the ’x’ argument. LaTeX code is also stored
in the same folder with the same name but .tex extension. When ’compile’ ar-
gument is FALSE, only .tex file is saved.
which.table character indicating which table is printed. Possible values are ’descr’, ’avail’ or
’both’ (partial matching allowed), printing descriptives by groups table, avail-
ability data table or both tables, respectively. Default value is ’descr’.
nmax logical, indicating whether to show the number of subjects with at least one valid
value across all row-variables. Default value is TRUE.
header.labels a character named vector with ’all’, ’p.overall’, ’p.trend’, ’ratio’, ’p.ratio’ and
’N’ components indicating the label for ’[ALL]’, ’p.overall’, ’p.trend’, ’ratio’,
’p.ratio’ and ’N’ (available data), respectively. Default is a zero length vector
which makes no changes, i.e. ’[ALL]’, ’p.overall’, ’p.trend’, ’ratio’, ’p.ratio’
and ’N’ labels appear for descriptives of entire cohort, global p-value, p-value
for trend, HR/OR and p-value of each HR/OR and available data, respectively.
caption character specifying the table caption for descriptives and available data table. If
which.table=’both’ the first element of ’caption’ will be assigned to descriptives
table and the second to available data table. If it is set to "", no caption is
inserted. Default value is NULL, which writes ’Summary descriptives table by
groups of ’y” for descriptives table and ’Available data by groups of ’y” for the
available data table.
width character string to specify the width of first column of descriptive table. Default
value is Inf which makes the first column to autoadjust to variable names. Other
examples are ’10cm’, ’3in’ or ’30em’.
strip logical. It shadows table lines corresponding to each variable.
first.strip logical. It determines whether to shadow the first variable (TRUE) or the second
(FALSE). It only applies when strip argument is true.
32 export2pdf

background color code in HEX format for shadowed lines. You can use rgb function to
convert red, green and blue to HEX code. Default color is ’#D2D2D2’.
size numeric. Size of descriptive table. Default value is NULL which creates the
table in default size.
landscape logical. It determines whether to place the table in landscape (horizontal) format.
It only applies when format is ’latex’. Default value is FALSE.
numcompiled integer. Number of times LaTeX code is compiled. When creating the table it
may be necessary to execute the code several times in order to fit the columns
widths. By default it is compiled twice.
header.background
color character for table header or ’NULL’. Default value is ’NULL’.
header.color color character for table header text. Default color is ’NULL’.

Note
To make the .tex file be compiled, some LaTeX compiler such as Miktex must be installed. Also,
the tex file must include the following LaTeX packages:
• longtable

• multirow

• multicol

• booktabs

• xcolor

• colortbl

• lscape

See Also
createTable, export2latex, export2csv, export2html, export2md, export2word

Examples

## Not run:

require(compareGroups)
data(regicor)

# example on an ordinary table

res <- createTable(compareGroups(year ~ . -id, regicor), hide = c(sex=1), hide.no = 'no')
export2word 33

export2pdf(res, file=tempfile(fileext=".pdf"), size="small")

## End(Not run)

export2word Exports tables to Word files.

Description
This function creates automatically a Word file with the table.

Usage
export2word(x, file, which.table="descr", nmax=TRUE, header.labels=c(),
caption=NULL, strip=FALSE, first.strip=FALSE, background="#D2D2D2",
size=NULL, header.background=NULL, header.color=NULL)

Arguments
x an object of class ’createTable’ or that inherits it.
file character specifying the word file (.doc or .docx) resulting after compiling the
Markdown code corresponding to the table specified in the ’x’ argument.
which.table character indicating which table is printed. Possible values are ’descr’ or ’avail’(partial
matching allowed), exporting descriptives by groups table or availability data ta-
ble, respectively. Default value is ’descr’.
nmax logical, indicating whether to show the number of subjects with at least one valid
value across all row-variables. Default value is TRUE.
header.labels see the ’header.labels’ argument from createTable.
caption character specifying the table caption for descriptives and available data table. If
which.table=’both’ the first element of ’caption’ will be assigned to descriptives
table and the second to available data table. If it is set to "", no caption is
inserted. Default value is NULL, which writes ’Summary descriptives table by
groups of ’y” for descriptives table and ’Available data by groups of ’y” for the
available data table.
strip logical. It shadows table lines corresponding to each variable.
first.strip logical. It determines whether to shadow the first variable (TRUE) or the second
(FALSE). It only applies when strip argument is true.
background color code in HEX format for shadowed lines. You can use rgb function to
convert red, green and blue to HEX code. Default color is ’#D2D2D2’.
size numeric. Size of descriptive table. Default value is NULL which creates the
table in default size.
header.background
color character for table header or ’NULL’. Default value is ’NULL’.
header.color color character for table header text. Default color is ’NULL’.
34 export2xls

Note
Word file is created after compiling Markdown code created by export2md. To compile it it calls
render function which requires pandoc to be installed.

See Also
createTable, export2latex, export2pdf, export2csv, export2html, export2md

Examples

## Not run:

require(compareGroups)
data(regicor)

# example on an ordinary table

res <- createTable(compareGroups(year ~ . -id, regicor), hide = c(sex=1), hide.no = 'no')
export2word(res, file = tempfile(fileext=".docx"))

## End(Not run)

export2xls Exporting descriptives table to Exel format (.xlsx or .xls)

Description
This function takes the result of createTable and exports the tables to Excel format (.xlsx or .xls).

Usage
export2xls(x, file, which.table="descr", nmax=TRUE, header.labels=c())

Arguments
x an object of class ’createTable’.
file file where table in Excel format will be written.
which.table character indicating which table is printed. Possible values are ’descr’, ’avail’ or
’both’ (partial matching allowed), exporting descriptives by groups table, avail-
ability data table or both tables, respectively. In the latter case (’both’), two
sheets are built, one for each table. Default value is ’descr’.
nmax logical, indicating whether to show the number of subjects with at least one valid
value across all row-variables. Default value is TRUE.
header.labels see the ’header.labels’ argument from createTable.
getResults 35

Note
The way to compute the ’N’ shown in the bivariate table header, controlled by ’nmax’ argument,
has been changed from previous versions (<1.3). In the older versions ’N’ was computed as the
maximum across the cells withing each column (group) from the ’available data’ table (’avail’).

See Also
createTable, export2latex, export2pdf, export2csv, export2md, export2word

Examples

## Not run:
require(compareGroups)
data(regicor)
res <- compareGroups(sex ~. -id-todeath-death-tocv-cv, regicor)
export2xls(createTable(res, hide.no = 'n'), file=tempfile(fileext=".xlsx"))

## End(Not run)

getResults Easily retrieve summary data as R-objects (matrices and vectors).

Description
This functions excratcs specific results (descriptives, p-values, Odds-Ratios / Hazard-Ratios, ...)
from a compareGroups object as matrix or vectors.

Usage
getResults(obj, what = "descr")

Arguments
obj an object of class ’compareGroups’ or ’createTable’
what character indicating which results are to be retrieved: decriptives, p-value, p-
trend, pairwise p-values, or Odds-Ratios / Hazard-Ratios. Possible values are:
"descr", "p.overall", "p.trend", "p.mul" and "ratio". Default value is "descr".

Value
what = "descr" An array or matrix with as many columns as variables/categories and seven
columns indicating all possible descriptive statistics (mean, sd, median, Q1, Q3,
absolute and relative frequencies). When different groups are analysed, the 3rd
dimension of the array corresponds to the groups. Otherwise, the result will be
a matrix with no 3rd dimension.
36 missingTable

what = "p.overall"
A vector whose elevements are the p-value for each analysed variable.
what = "p.trend"
A vector whose elevements are the p-trend for each analysed variable.
what = "p.mul" A matrix with pairwise p-values where rows correspond to the analysed vari-
ables and columns to each pair of groups.
what = "ratio" A matrix with as many rows as variables/categorieswith and 4 columns corre-
sponding to the OR/HR, confidence interval and p-value.

Note
For descriptives, NA is placed for descriptives not appropiate for the variable. For example columns
corresponding to frequencies for continuous variables will be NA.

See Also
compareGroups, createTable

Examples
require(compareGroups)
data(regicor)
res<-compareGroups(sex ~ . ,regicor,method=c(triglyc=2))
# retrieve descriptives
getResults(res)
# retrieve OR and their corresponding p-values
getResults(res,what="ratio")

missingTable Table of missingness counts by groups.

Description
This functions returns a table with the non-available frequencies from a already build bivariate table.

Usage
missingTable(obj,...)

Arguments
obj either a ’compareGroups’ or ’createTable’ object.
... other arguments passed to createTable.

Value
An object of class ’createTable’. For further details, see ’value’ section of createTable help file.
missingTable 37

Note
This function returns an object of class ’createTable’, and therefore all methods implemented for
’createTable’ objects can be applied, except the ’update’ method.
All arguments of createTable can be passed throught ’...’ argument, except ’hide.no’ argument
which is fixed inside the code and cannot be changed.
This function cannot be applied to stratified tables, i.e. ’rbind.createTable’ and ’cbind.createTable’.
If stratified missingness table is desired, apply this function first to each table and then use cbind.createTable
or/and rbind.createTable functions to combine exactly in the same way as ’createTable’ objects.
See ’example’ section below.

See Also
createTable

Examples

require(compareGroups)

# load regicor data

data(regicor)

# table of descriptives by recruitment year

res <- compareGroups(year ~ age + sex + smoker + sbp + histhtn +
chol + txchol + bmi + phyact + pcs + death, regicor)
restab <- createTable(res, hide.no = "no")

# missingness table
missingTable(restab,type=1)

## Not run:

# also create the missing table from a compareGroups object

miss <- missingTable(res)
miss

# some methods that works for createTable objects also works for objects
# computed by missTable function.
miss[1:4]
varinfo(miss)
plot(miss)

#... but update methods cannot be applied (this returns an error).

update(miss,type=2)

## End(Not run)
38 padjustCompareGroups

padjustCompareGroups Update p values according multiple comparisons

Description
Given a compareGroups object, returns their p-values adjusted using one of several methods (stats::p.adjust)

Usage
padjustCompareGroups(object_compare, p = "p.overall", method = "BH")

Arguments
object_compare object of class compareGroups
p character string. Specify which p-value must be corrected. Possible values are
’p.overall’ and ’p.trend’ (default: ’p.overall’)
method Correction method, a character string. Can be abbreviated (see p.adjust).

Value
compareGroups class with corrected p-values

Author(s)
Jordi Real <jordireal<at>gmail.com>

Examples
# Define simulated data
set.seed(123)
N_obs<-100
N_vars<-50
data<-matrix(rnorm(N_obs*N_vars), N_obs, N_vars)

sim_data<-data.frame(data,Y=rbinom(N_obs,1,0.5))

# Execute compareGroups
res<-compareGroups(Y~.,data=sim_data)
res

# update p values
res_adjusted<-padjustCompareGroups(res)
res_adjusted

# update p values using FDR method

res_adjusted<-padjustCompareGroups(res, method ="fdr")
res_adjusted
printTable 39

printTable ’Nice’ table format.

Description
This functions prints a table on the console in a ’nice’ format.

Usage
printTable(obj, row.names = TRUE, justify = 'right')

Arguments
obj an object of class ’data.frame’ or ’matrix’. It must be at least two columns,
the first columns is considered as the ’row.names’ and is left justified (if the
’row.names’ argument is set to TRUE), while the rest of the columns are right
justified.
row.names logical indicating whether the first column or variable is treated as a ’row.names’
column and must be left-justified. Default value is TRUE.
justify character as ’justify’ argument from format function. It applies to all columns
of the data.frame or matrix when ’row.names’ argument is FALSE or all columns
excluding the first one otherwise. Default value is ’right’.

Value
No object is returned.

Note
This function may be usefull when printing a table with some results with variables as the first
column and a header. It adds ’nice’ lines to highlight the header and also the bottom of the table.
It has been used to print ’compareSNPs’ objects.

See Also
compareSNPs

Examples

require(compareGroups)

data(regicor)

# example of the coefficients table from a linear regression

model <- lm(chol ~ age + sex + bmi, regicor)
results <- coef(summary(model))
results <- cbind(Var = rownames(results), round(results, 4))
40 radiograph

printTable(results)

# or visualize the first rows of the iris data frame.

# In this example, the first column is not treated as a row.names column and it is right justified.
printTable(head(iris), FALSE)

# the same example with columns centered

printTable(head(iris), FALSE, 'centre')

radiograph Lists the values in the data set.

Description

This function creates a report of raw data in your data set. For each variable an ordered list of the
unique entries (read as strings), useful for checking for input errors.

Usage

radiograph(file, header = TRUE, save=FALSE, out.file="", ...)

Arguments

file character specifying the file where the data set is located.
header see read.table.
save logical indicating whether output should be stored in a file (TRUE) or printed
on the console (FALSE). Default is FALSE.
out.file character specifying the file where the results are to be output. It only applies
when ’save’ argument is set to TRUE.
... Arguments passed to read.table.

Author(s)

Gavin Lucas (gavin.lucas<at>cleargenetics.com)

Isaac Subirana (isubirana<at>imim.es)

See Also

report
regicor 41

Examples

## Not run:

require(compareGroups)

# read example data of regicor in plain text format with variables separated by '\t'.
datafile <- system.file("exdata/regicor.txt", package="compareGroups")
radiograph(datafile)

## End(Not run)

regicor REGICOR cross-sectional data

Description
These data come from 3 different cross-sectional surveys of individuals representative of the popu-
lation from a north-west Spanish province (Girona), REGICOR study.

Usage
data(regicor)

Format
A data frame with 2294 observations on the following 21 variables:

id Individual id
year a factor with levels 1995 2000 2005. Recruitment year
age Patient age at recruitment date
sex a factor with levels male female. Sex
smoker a factor with levels Never smoker Current or former < 1y Never or former >= 1y. Smok-
ing status
sbp Systolic blood pressure
dbp Diastolic blood pressure
histhtn a factor with levels Yes No. History of hypertension
txhtn a factor with levels No Yes. Hypertension (HTN) treatment
chol Total cholesterol (mg/dl)
hdl HDL cholesterol (mg/dl)
triglyc Triglycerides (mg/dl)
ldl LDL cholesterol (mg/dl)
42 regicor

histchol a factor with levels Yes No. History of hypercholesterolemia

txchol a factor with levels No Yes. Cholesterol treatment
height Height (cm)
weight Weight (Kg)
bmi Body mass index
phyact Physical activity (Kcal/week)
pcs Physical component summary
mcs Mental component summary
death a factor with levels No Yes. Overall death
todeath Days to overall death or end of follow-up
cv a factor with levels No Yes. Cardiovascular event
tocv Days to cardiovascular event or end of follow-up

Details

The variables collected in the REGICOR study were mainly cardiovascular risk factors (hundreds of
variables were collected in the different questionnaires and blood measurements), but the variables
present in this data set are just a few of them. Also, for reasons of confidentiality, the individuals in
this data set are a 30% approx. random subsample of the original one.

Each variable of this data.frame contains label describing them in the attribute "label".

For more information, see the vignette.

Note

Variables death, todeath, cv, tocv are not real but they have been simulated at random to complete
the data example with some time-to-event variables.

Source

For reasons of confidentiality, the whole data set is not publicly available. For more information
about the study these data come from, visit www.regicor.org.

Examples
require(compareGroups)
data(regicor)
summary(regicor)
report 43

report Report of descriptive tables and plots.

Description
This function creates automatically a PDF with the descriptive table as well as availability data and
all plots. This file is structured and indexed in the way that the user can navigate through all tables
and figures along the document.

Usage
report(x, file, fig.folder, compile = TRUE, openfile = FALSE, title = "Report",
author, date, perc=FALSE, ...)

Arguments
x an object of class ’createTable’.
file character specifying the PDF file resulting after compiling the LaTeX code of
report. LaTeX code is also stored in the same folder with the same name but .tex
extension. When ’compile’ argument is FALSE, only .tex file is saved.
fig.folder character specifying the folder where the plots corresponding to all row-variables
of the table are placed. If it is left missing, a folder with the name file_figures is
created in the same folder of ’file’.
compile logical indicating whether tex file is compiled using texi2pdf function. Default
value is TRUE.
openfile logical indicating whether to open the compiled pdf file or not. Currently deprec-
tated. Deafult value is FALSE.
title character specifying the title of the report on the cover page. Default value is
’Report’.
author character specifying the author/s name/s of the report on the cover page. When
missing, no authors appear.
date character specifying the date of the report on the cover page. When missing, the
present date appears.
perc logical. Plot relative frequencies (in percentatges) instead of absolute frequen-
cies are displayed in barplots for categorical variable.
... Arguments passed to export2latex.

Note
This functions does not work with stratified tables (’cbind.createTable’ class objects). To report this
class of tables you can report each of its component (see second example from ’examples’ section).
In order to compile the tex file the following packages must be available:
- babel
- longtable
44 SNPs

- hyperref
- multirow
- lscape
- geometry
- float
- inputenc
- epsfig

See Also
createTable, export2latex, export2csv, export2html, radiograph

Examples

## Not run:

require(compareGroups)
data(regicor)

# example on an ordinary table

res <- createTable(compareGroups(year ~ . -id, regicor), hide = c(sex=1), hide.no = 'no')
report(res, "report.pdf" ,size="small", title="\Huge \textbf{REGICOR study}",
author="Isaac Subirana \\ IMIM-Parc de Salut Mar")

# example on an stratified table by sex

res.men <- createTable(compareGroups(year ~ . -id-sex, regicor, subset=sex=='Male'),
hide.no = 'no')
res.wom <- createTable(compareGroups(year ~ . -id-sex, regicor, subset=sex=='Female'),
hide.no = 'no')
res <- cbind("Men"=res.men, "Wom"=res.wom)
report(res[[1]], "reportmen.pdf", size="small",
title="\Huge \textbf{REGICOR study \\ Men}", date="") # report for men / no date
report(res[[2]], "reportwom.pdf", size="small",
title="\Huge \textbf{REGICOR study \\ Women}", date="") # report for wom / no date

## End(Not run)

SNPs SNPs in a case-control study

Description
SNPs data.frame contains selected SNPs and other clinical covariates for cases and controls in a
case-control study
SNPs.info.pos data.frame contains the names of the SNPs included in the data set ’SNPs’ including
their chromosome and their genomic position
strataTable 45

Usage
data(SNPs)

Format
’SNPs’ data.frame contains the following columns:

id identifier of each subject

casco case or control status: 0-control, 1-case
sex gender: Male and Female
blood.pre arterial blood presure
protein protein levels
snp10001 SNP 1
snp10002 SNP 2
... ...
snp100036 SNP 36

’SNPs.info.pos’ data.frame contains the following columns: A data frame with 35 observations on
the following 3 variables.

snp name of SNP

chr name of chromosome
pos genomic position

Source
Data obtained from the <code>SNPassoc</code> package.

strataTable Stratify descriptive table in stratas.

Description
This functions re-build a descriptive table in stratas defined by a variable.

Usage
strataTable(x, strata, strata.names = NULL, max.nlevels = 5)

Arguments
x an object of class ’createTable’
strata character specifying the name of the variable whose values or levels defines
strata.
46 varinfo

strata.names character vector with as many components as stratas, or NULL (default value).
If NULL, it takes the names of levels of strata variable.
max.nlevels an integer indicating the maximum number of unique values or levels of strata
variable. Default value is 5.

Value
An object of class ’cbind.createTable’.

References
Isaac Subirana, Hector Sanz, Joan Vila (2014). Building Bivariate Tables: The compareGroups
Package for R. Journal of Statistical Software, 57(12), 1-16. URL https://www.jstatsoft.org/
v57/i12/.

See Also
compareGroups, createTable, descrTable

Examples

require(compareGroups)

# load REGICOR data

data(regicor)

# compute the descriptive tables (by year)

restab <- descrTable(year ~ . - id - sex, regicor, hide.no="no")

# re-build the table stratifying by gender

strataTable(restab, "sex")

varinfo Variable names and labels extraction

Description
This functions builds and prints a table with the variable names and their labels.

Usage
varinfo(x, ...)
## S3 method for class 'compareGroups'
varinfo(x, ...)
## S3 method for class 'createTable'
varinfo(x, ...)
varinfo 47

Arguments
x an object of class ’compareGroups’ or ’createTable’
... other arguments currently ignored

Details
By default, a compareGroup descriptives table lists variables by label (if one exists) rather than by
name. If researchers have assigned detailed labels to their variables, this function is very useful to
quickly locate the original variable name if some modification is required. This function simply
lists all "Analyzed variable names" by "Orig varname" (i.e. variable name in the data.frame) and
"Shown varname" (i.e., label).

Value
A ’matrix’ with two columns

Orig varname actual variable name in the ’data.frame’ or in the ’parent environment’.
Shown varname names of the variable shown in the resulting tables.

Note
If a variable has no "label" attribute, then the ’original varname’ is the same as the ’shown varname’.
The first variable in the table corresponds to the grouping variable. To label non-labeled variables
or to change the label, specify its "label" attribute..

See Also
compareGroups, createTable

Examples
require(compareGroups)
data(regicor)
res<-compareGroups(sex ~ . ,regicor)
#createTable(res, hide.no = 'no')
varinfo(res)
Index

∗ datasets createTable, 3, 4, 11, 14, 14, 22, 24–30,

regicor, 41 32–37, 44, 46, 47
SNPs, 44
∗ misc descrTable, 3, 19, 46
compareGroups, 5
compareSNPs, 12 export2csv, 3, 17, 24, 24, 26, 28, 30, 32, 34,
createTable, 14 35, 44
descrTable, 19 export2html, 3, 17, 24, 25, 25, 28, 30, 32, 34,
44
strataTable, 45
export2latex, 3, 17, 24–26, 26, 30, 32, 34,
∗ package
35, 43, 44
compareGroups-package, 2
export2md, 3, 25, 26, 28, 28, 32, 34, 35
∗ utilities
export2pdf, 3, 25, 26, 28, 30, 31, 34, 35
cGroupsGUI, 3
export2word, 3, 25, 26, 28, 30, 32, 33, 35
cGroupsWUI, 4
export2xls, 3, 34
export2csv, 24
export2html, 25 fisher.test, 8, 21
export2latex, 26 format, 39
export2md, 28
export2pdf, 31 getResults, 35
export2word, 33
export2xls, 34 hist, 9
getResults, 35 HWChisq, 12
missingTable, 36 HWChisqMat, 13
printTable, 39
radiograph, 40 jpeg, 9, 10
report, 43
kable, 29
varinfo, 46
kable_styling, 29
.GlobalEnv, 6, 20
missingTable, 3, 36
anova, 8, 22
na.exclude, 6, 12, 19
bmp, 9, 10 na.pass, 6, 12, 19
cGroupsGUI, 3, 3, 4 oneway.test, 8, 22
cGroupsWUI, 3, 4, 4
chisq.test, 8, 21 p.adjust, 38
chron, 8, 22 padjustCompareGroups, 38
compareGroups, 3, 4, 5, 17, 19, 24, 36, 46, 47 pdf, 9, 10
compareGroups-package, 2 plot.compareGroups (compareGroups), 5
compareSNPs, 3, 12, 39 plot.createTable (createTable), 14

48
INDEX 49

png, 9, 10
print.compareGroups (compareGroups), 5
print.compareSNPs (compareSNPs), 12
print.createTable (createTable), 14
print.default, 16
print.summary.compareGroups
(compareGroups), 5
print.summary.createTable
(createTable), 14
printTable, 39

radiograph, 3, 40, 44
read.table, 40
regicor, 41
render, 34
report, 3, 40, 43
runApp, 4

shapiro.test, 6, 20
SNPs, 44
strataTable, 3, 45
summary.compareGroups (compareGroups), 5
summary.createTable (createTable), 14

texi2pdf, 43
tiff, 9, 10

update.compareGroups (compareGroups), 5

varinfo, 46

write.table, 25