Title: | Easy Table |
---|---|
Description: | Creates simple to highly customized tables for a wide selection of descriptive statistics, with or without weighting the data. |
Authors: | Andreas Schulz [aut, cre] |
Maintainer: | Andreas Schulz <[email protected]> |
License: | GPL (>= 3) |
Version: | 1.3.1 |
Built: | 2024-12-16 06:52:59 UTC |
Source: | CRAN |
The package comes without any warranty.
Package: | etable |
Title: | Easy Table |
Type: | Package |
Version: | 1.3.0 |
Date: | 2021-05-23 |
Depends: | R (>= 3.0.0) |
Imports: | xtable, Hmisc |
License: | GPL version 3 or newer |
LazyLoad: | yes |
Andreas Schulz
Maintainer: <[email protected]>
Calculates different statistics depending on the type of variable.
combi_cell(x, y, z, w, cell_ids, row_ids, col_ids, vnames, vars, n_min, digits=3, style=1)
combi_cell(x, y, z, w, cell_ids, row_ids, col_ids, vnames, vars, n_min, digits=3, style=1)
x |
The x variable for calculations, if not using y |
y |
The y variable for calculations, if not using x |
z |
NOT USED |
w |
Weights for x or y variable. |
cell_ids |
Index vector for selecting values in cell. |
row_ids |
NOT USED |
col_ids |
NOT USED |
vnames |
NOT USED |
vars |
NOT USED |
n_min |
Minimum n in the cell for useful calculation. Cells with n<n_min deliver no output. |
digits |
Integer indicating the number of significant digits. |
style |
Type of representation.
|
Andreas Schulz <[email protected]>
sex <- factor(rbinom(1000, 1, 0.4), labels=c('Men', 'Women')) height <- rnorm(1000, mean=1.7, sd=0.1) weight <- rnorm(1000, mean=70, sd=5) bmi <- weight/height^2 event <- factor(rbinom(1000, 1, 0.1), labels=c('no', 'yes')) d<-data.frame(sex, height, weight, bmi, event) tabular.ade(x_vars=names(d), cols=c('sex','ALL'), rnames=c('Gender'), data=d, FUN=combi_cell)
sex <- factor(rbinom(1000, 1, 0.4), labels=c('Men', 'Women')) height <- rnorm(1000, mean=1.7, sd=0.1) weight <- rnorm(1000, mean=70, sd=5) bmi <- weight/height^2 event <- factor(rbinom(1000, 1, 0.1), labels=c('no', 'yes')) d<-data.frame(sex, height, weight, bmi, event) tabular.ade(x_vars=names(d), cols=c('sex','ALL'), rnames=c('Gender'), data=d, FUN=combi_cell)
Calculating Pearson product-moment correlation coefficient.
corr_p_cell(x, y, z, w, cell_ids, row_ids, col_ids, vnames, vars, n_min, digits = 3)
corr_p_cell(x, y, z, w, cell_ids, row_ids, col_ids, vnames, vars, n_min, digits = 3)
x |
The x variable |
y |
The y variable |
z |
NOT USED |
w |
Weights for x and y variable. |
cell_ids |
Index vector for selecting values in cell. |
row_ids |
NOT USED |
col_ids |
NOT USED |
vnames |
NOT USED |
vars |
NOT USED |
n_min |
Minimum n in the cell for useful calculation. Cells with n<n_min deliver no output. |
digits |
Integer indicating the number of decimal places. |
Andreas Schulz <[email protected]>
sex <- factor(rbinom(1000, 1, 0.4), labels=c('Men', 'Women')) height <- rnorm(1000, mean=1.70, sd=0.1) weight <- rnorm(1000, mean=70, sd=5) bmi <- weight/height^2 d<-data.frame(sex, bmi, height, weight) tabular.ade(x_vars=c('bmi','height','weight'), xname=c('BMI','Height','Weight'), y_vars=c('bmi','height','weight'), yname=c('BMI','Height','Weight'), rows=c('sex','ALL'), rnames=c('Gender'), data=d, FUN=corr_p_cell)
sex <- factor(rbinom(1000, 1, 0.4), labels=c('Men', 'Women')) height <- rnorm(1000, mean=1.70, sd=0.1) weight <- rnorm(1000, mean=70, sd=5) bmi <- weight/height^2 d<-data.frame(sex, bmi, height, weight) tabular.ade(x_vars=c('bmi','height','weight'), xname=c('BMI','Height','Weight'), y_vars=c('bmi','height','weight'), yname=c('BMI','Height','Weight'), rows=c('sex','ALL'), rnames=c('Gender'), data=d, FUN=corr_p_cell)
Calculates frequencies or proportions of a certain level of factor x.
eventpct_cell(x, y, z, w, cell_ids, row_ids, col_ids, vnames, vars, n_min, digits=1, digits2=0, event=2, type=1)
eventpct_cell(x, y, z, w, cell_ids, row_ids, col_ids, vnames, vars, n_min, digits=1, digits2=0, event=2, type=1)
x |
The factor x for calculations |
y |
NOT USED |
z |
NOT USED |
w |
Weights for x factor, only if calculating weighted frequencies. |
cell_ids |
Index vector for selecting values in cell. |
row_ids |
NOT USED |
col_ids |
NOT USED |
vnames |
NOT USED |
vars |
NOT USED |
n_min |
Minimum n in the cell for useful calculation. Cells with n<n_min deliver no output. |
digits |
Integer indicating the number of decimal places (for percentages) |
digits2 |
Integer indicating the number of decimal places (N, needed if N is not integer because of weighting) |
event |
The Number of factor level to calculate frequencies. from 1 to nlevels(x) |
type |
Type of representation, one of following.
|
Andreas Schulz <[email protected]>
sex <- factor(rbinom(1000, 1, 0.4), labels=c('Men', 'Women')) event <- factor(rbinom(1000, 1, 0.1), labels=c('no', 'yes')) decades <- rbinom(1000, 3, 0.5) decades <- factor(decades, labels=c('[35,45)','[45,55)','[55,65)','[65,75)')) d<-data.frame(sex, decades, event) tabular.ade(x_vars=c('event'), xname=c('Event'), rows=c('sex','ALL'), rnames=c('Gender'), cols=c('decades', 'ALL'), cnames=c('Age decades'), data=d, FUN=eventpct_cell)
sex <- factor(rbinom(1000, 1, 0.4), labels=c('Men', 'Women')) event <- factor(rbinom(1000, 1, 0.1), labels=c('no', 'yes')) decades <- rbinom(1000, 3, 0.5) decades <- factor(decades, labels=c('[35,45)','[45,55)','[55,65)','[65,75)')) d<-data.frame(sex, decades, event) tabular.ade(x_vars=c('event'), xname=c('Event'), rows=c('sex','ALL'), rnames=c('Gender'), cols=c('decades', 'ALL'), cnames=c('Age decades'), data=d, FUN=eventpct_cell)
For calculate median and interquartile range. (weighting is possible)
iqr_cell(x, y, z, w, cell_ids, row_ids, col_ids, vnames, vars, n_min, digits = 3, add_n=FALSE)
iqr_cell(x, y, z, w, cell_ids, row_ids, col_ids, vnames, vars, n_min, digits = 3, add_n=FALSE)
x |
The x variable for calculations |
y |
NOT USED |
z |
NOT USED |
w |
Weights for x variable. |
cell_ids |
Index vector for selecting values in cell. |
row_ids |
NOT USED |
col_ids |
NOT USED |
vnames |
NOT USED |
vars |
NOT USED |
n_min |
Minimum n in the cell for useful calculation. Cells with n<n_min deliver no output. |
digits |
Integer indicating the number of significant digits. |
add_n |
Logical asking whether to draw N for each cell. |
Andreas Schulz <[email protected]>
sex <- factor(rbinom(1000, 1, 0.4), labels=c('Men', 'Women')) height <- rnorm(1000, mean=1.66, sd=0.1) height[which(sex=='Men')]<-height[which(sex=='Men')]+0.1 weight <- rnorm(1000, mean=70, sd=5) decades <- rbinom(1000, 3, 0.5) decades <- factor(decades, labels=c('[35,45)','[45,55)','[55,65)','[65,75)')) d<-data.frame(sex, decades, height, weight) tabular.ade(x_vars=c('height', 'weight'), xname=c('Height [m]','Weight [kg]'), rows=c('sex','ALL'), rnames=c('Gender'), cols=c('decades'), cnames=c('Age decades'), data=d, FUN=iqr_cell, add_n=TRUE)
sex <- factor(rbinom(1000, 1, 0.4), labels=c('Men', 'Women')) height <- rnorm(1000, mean=1.66, sd=0.1) height[which(sex=='Men')]<-height[which(sex=='Men')]+0.1 weight <- rnorm(1000, mean=70, sd=5) decades <- rbinom(1000, 3, 0.5) decades <- factor(decades, labels=c('[35,45)','[45,55)','[55,65)','[65,75)')) d<-data.frame(sex, decades, height, weight) tabular.ade(x_vars=c('height', 'weight'), xname=c('Height [m]','Weight [kg]'), rows=c('sex','ALL'), rnames=c('Gender'), cols=c('decades'), cnames=c('Age decades'), data=d, FUN=iqr_cell, add_n=TRUE)
Calculates mean and SD or weighted mead and SD.
mean_sd_cell(x, y, z, w, cell_ids, row_ids, col_ids, vnames, vars, n_min, digits = 3, style=1, nsd=1)
mean_sd_cell(x, y, z, w, cell_ids, row_ids, col_ids, vnames, vars, n_min, digits = 3, style=1, nsd=1)
x |
The x variable for calculations |
y |
NOT USED |
z |
NOT USED |
w |
Weights for x variable. |
cell_ids |
Index vector for selecting values in cell. |
row_ids |
NOT USED |
col_ids |
NOT USED |
vnames |
NOT USED |
vars |
NOT USED |
n_min |
Minimum n in the cell for useful calculation. Cells with n<n_min deliver no output. |
digits |
Integer indicating the number of significant digits. |
style |
Type of representation.
|
nsd |
Multiplier for sd in stlyle 2. (for normal distribution)
|
Andreas Schulz <[email protected]>
sex <- factor(rbinom(1000, 1, 0.4), labels=c('Men', 'Women')) height <- rnorm(1000, mean=1.66, sd=0.1) height[which(sex=='Men')]<-height[which(sex=='Men')]+0.1 weight <- rnorm(1000, mean=70, sd=5) decades <- rbinom(1000, 3, 0.5) decades <- factor(decades, labels=c('[35,45)','[45,55)','[55,65)','[65,75)')) d<-data.frame(sex, decades, height, weight) tabular.ade(x_vars=c('height', 'weight'), xname=c('Height [m]','Weight [kg]'), rows=c('sex','ALL'), rnames=c('Gender'), cols=c('decades'), cnames=c('Age decades'), data=d, FUN=mean_sd_cell, style=2, nsd=1.96)
sex <- factor(rbinom(1000, 1, 0.4), labels=c('Men', 'Women')) height <- rnorm(1000, mean=1.66, sd=0.1) height[which(sex=='Men')]<-height[which(sex=='Men')]+0.1 weight <- rnorm(1000, mean=70, sd=5) decades <- rbinom(1000, 3, 0.5) decades <- factor(decades, labels=c('[35,45)','[45,55)','[55,65)','[65,75)')) d<-data.frame(sex, decades, height, weight) tabular.ade(x_vars=c('height', 'weight'), xname=c('Height [m]','Weight [kg]'), rows=c('sex','ALL'), rnames=c('Gender'), cols=c('decades'), cnames=c('Age decades'), data=d, FUN=mean_sd_cell, style=2, nsd=1.96)
Counting the number of missing values in each cell.
miss_cell(x, y, z, w, cell_ids, row_ids, col_ids, vnames, vars, n_min, pct = FALSE, digits = 0, prefix='', suffix='')
miss_cell(x, y, z, w, cell_ids, row_ids, col_ids, vnames, vars, n_min, pct = FALSE, digits = 0, prefix='', suffix='')
x |
The x variable |
y |
NOT USED |
z |
NOT USED |
w |
NOT USED (The number of missing will not be weighted!). |
cell_ids |
Index vector for selecting values in cell. |
row_ids |
NOT USED |
col_ids |
NOT USED |
vnames |
NOT USED |
vars |
NOT USED |
n_min |
NOT USED |
pct |
Logical asking whatever to draw absolute or relative frequency of missing values. |
digits |
Integer indicating the number of decimal places. |
prefix |
Free text added in each cell bevor results. |
suffix |
Free text added in each cell after results. |
Andreas Schulz <[email protected]>
sex <- factor(rbinom(1000, 1, 0.4), labels=c('Men', 'Women')) height <- rnorm(1000, mean=1.66, sd=0.1) height[which(sex=='Men')]<-height[which(sex=='Men')]+0.1 weight <- rnorm(1000, mean=70, sd=5) decades <- rbinom(1000, 3, 0.5) decades <- factor(decades, labels=c('[35,45)','[45,55)','[55,65)','[65,75)')) d<-data.frame(sex, decades, height, weight) d$height[round(runif(250,1,1000))]<- NA d$weight[round(runif(25 ,1,1000))]<- NA tabular.ade(x_vars=c('height', 'weight'), xname=c('Height [m]','Weight [kg]'), cols=c('sex','decades','ALL'), cnames=c('Gender', 'Age decades'), data=d, FUN=miss_cell, prefix='Miss:')
sex <- factor(rbinom(1000, 1, 0.4), labels=c('Men', 'Women')) height <- rnorm(1000, mean=1.66, sd=0.1) height[which(sex=='Men')]<-height[which(sex=='Men')]+0.1 weight <- rnorm(1000, mean=70, sd=5) decades <- rbinom(1000, 3, 0.5) decades <- factor(decades, labels=c('[35,45)','[45,55)','[55,65)','[65,75)')) d<-data.frame(sex, decades, height, weight) d$height[round(runif(250,1,1000))]<- NA d$weight[round(runif(25 ,1,1000))]<- NA tabular.ade(x_vars=c('height', 'weight'), xname=c('Height [m]','Weight [kg]'), cols=c('sex','decades','ALL'), cnames=c('Gender', 'Age decades'), data=d, FUN=miss_cell, prefix='Miss:')
Shows the most frequent value (mode)
mode_cell(x, y, z, w, cell_ids, row_ids, col_ids, vnames, vars, n_min, digits=3)
mode_cell(x, y, z, w, cell_ids, row_ids, col_ids, vnames, vars, n_min, digits=3)
x |
The x variable |
y |
NOT USED |
z |
NOT USED |
w |
Weights for x variable. Only if calculating weighted mode. |
cell_ids |
Index vector for selecting values in cell. |
row_ids |
Index vector for selecting values in row. |
col_ids |
Index vector for selecting values in col. |
vnames |
NOT USED |
vars |
NOT USED |
n_min |
NOT USED |
digits |
Integer indicating the number of significant digits. |
Andreas Schulz <[email protected]>
sex <- factor(rbinom(1000, 1, 0.4), labels=c('Men', 'Women')) note <- as.factor(rbinom(1000, 4, 0.5)+1) decades <- rbinom(1000, 3, 0.5) decades <- factor(decades, labels=c('[35,45)','[45,55)','[55,65)','[65,75)')) d<-data.frame(sex, decades, note) tabular.ade(x_vars=c('note'), xname=c('Noten'), rows=c('sex','ALL','decades'), rnames=c('Gender', 'Age decades'), data=d, FUN=mode_cell)
sex <- factor(rbinom(1000, 1, 0.4), labels=c('Men', 'Women')) note <- as.factor(rbinom(1000, 4, 0.5)+1) decades <- rbinom(1000, 3, 0.5) decades <- factor(decades, labels=c('[35,45)','[45,55)','[55,65)','[65,75)')) d<-data.frame(sex, decades, note) tabular.ade(x_vars=c('note'), xname=c('Noten'), rows=c('sex','ALL','decades'), rnames=c('Gender', 'Age decades'), data=d, FUN=mode_cell)
For calculation of relative or absolute frequencies.
n_cell(x, y, z, w, cell_ids, row_ids, col_ids, vnames, vars, n_min, digits=0, digits2=1, type="n")
n_cell(x, y, z, w, cell_ids, row_ids, col_ids, vnames, vars, n_min, digits=0, digits2=1, type="n")
x |
The x variable (can be just 1:N if without missings values) |
y |
NOT USED |
z |
NOT USED |
w |
Weights for x variable. Only if calculating weigted frequences. |
cell_ids |
Index vector for selecting values in cell. |
row_ids |
Index vector for selecting values in row. |
col_ids |
Index vector for selecting values in col. |
vnames |
NOT USED |
vars |
NOT USED |
n_min |
NOT USED |
digits |
Integer indicating the number of decimal places (N) |
digits2 |
Integer indicating the number of decimal places (percentages) |
type |
Type of frequencies, one of following.
|
The function calculate frequencies for cell. If x has no missing values the frequencies are independent of x. Missing values in x will be removed from calculation.
Andreas schulz <[email protected]>
sex <- factor(rbinom(1000, 1, 0.4), labels=c('Men', 'Women')) decades <- rbinom(1000, 3, 0.5) decades <- factor(decades, labels=c('[35,45)','[45,55)','[55,65)','[65,75)')) d<-data.frame(sex, decades) tabular.ade(x_var='sex', rows=c('sex', 'ALL'), rnames=c('Gender'), cols=c('decades', 'ALL'), cnames=c('Age decades'), data=d, FUN=n_cell, , type="all")
sex <- factor(rbinom(1000, 1, 0.4), labels=c('Men', 'Women')) decades <- rbinom(1000, 3, 0.5) decades <- factor(decades, labels=c('[35,45)','[45,55)','[55,65)','[65,75)')) d<-data.frame(sex, decades) tabular.ade(x_var='sex', rows=c('sex', 'ALL'), rnames=c('Gender'), cols=c('decades', 'ALL'), cnames=c('Age decades'), data=d, FUN=n_cell, , type="all")
Calculating simple or weighted quantiles
quantile_cell(x, y, z, w, cell_ids, row_ids, col_ids, vnames, vars, n_min, digits = 3, probs = 0.5, plabels=FALSE)
quantile_cell(x, y, z, w, cell_ids, row_ids, col_ids, vnames, vars, n_min, digits = 3, probs = 0.5, plabels=FALSE)
x |
The x variable for calculations |
y |
NOT USED |
z |
NOT USED |
w |
Weights for x variable. |
cell_ids |
Index vector for selecting values in cell. |
row_ids |
NOT USED |
col_ids |
NOT USED |
vnames |
NOT USED |
vars |
NOT USED |
n_min |
Minimum n in the cell for useful calculation. Cells with n<n_min deliver no output. |
digits |
Integer indicating the number of significant digits. |
probs |
A single or a vector of numeric probabilities for sample quantile with values in [0,1]. |
plabels |
Logical asking whether to label the quantile in the cell or only draw the value. |
Andreas Schulz <[email protected]>
sex <- factor(rbinom(1000, 1, 0.4), labels=c('Men', 'Women')) height <- rnorm(1000, mean=1.66, sd=0.1) height[which(sex=='Men')]<-height[which(sex=='Men')]+0.1 weight <- rnorm(1000, mean=70, sd=5) decades <- rbinom(1000, 3, 0.5) decades <- factor(decades, labels=c('[35,45)','[45,55)','[55,65)','[65,75)')) d<-data.frame(sex, decades, height, weight) tabular.ade(x_vars=c('height', 'weight'), xname=c('Height [m]','Weight [kg]'), rows=c('sex', 'ALL'), rnames=c('Gender'), cols=c('decades', 'ALL'), cnames=c('Age decades'), data=d, FUN=quantile_cell, probs = 0.99)
sex <- factor(rbinom(1000, 1, 0.4), labels=c('Men', 'Women')) height <- rnorm(1000, mean=1.66, sd=0.1) height[which(sex=='Men')]<-height[which(sex=='Men')]+0.1 weight <- rnorm(1000, mean=70, sd=5) decades <- rbinom(1000, 3, 0.5) decades <- factor(decades, labels=c('[35,45)','[45,55)','[55,65)','[65,75)')) d<-data.frame(sex, decades, height, weight) tabular.ade(x_vars=c('height', 'weight'), xname=c('Height [m]','Weight [kg]'), rows=c('sex', 'ALL'), rnames=c('Gender'), cols=c('decades', 'ALL'), cnames=c('Age decades'), data=d, FUN=quantile_cell, probs = 0.99)
Calculating values of several descriptive statistics.
stat_cell(x, y, z, w, cell_ids, row_ids, col_ids, vnames, vars, n_min, digits = 3, digits2=1)
stat_cell(x, y, z, w, cell_ids, row_ids, col_ids, vnames, vars, n_min, digits = 3, digits2=1)
x |
The x variable |
y |
NOT USED |
z |
NOT USED |
w |
Weights for x variable. |
cell_ids |
Index vector for selecting values in cell. |
row_ids |
NOT USED |
col_ids |
NOT USED |
vnames |
NOT USED |
vars |
A vector of character strings with names of variables in data.frame for x, y and z. Use names of x or y as keywords, to choose a certain statistic. |
n_min |
Minimum n in the cell for useful calculation. Cells with n<n_min deliver no output. |
digits |
Integer indicating the number of significant digits. |
digits2 |
Integer indicating the number of decimal places for percentages. |
Keywords are:
N: number in this cell
MIN: minimum
MAX: maximum
SUM: sum
MEAN: mean
SD: standard deviation
MSD: mean, standard deviation
MCI: mean, 95% CI
VAR: variance
MEDIAN: median
MD: mean deviation from the mean (*1.253)
MAD: median absolute deviation (*1.4826)
IQR: interquartile range
MQQ: median (Q1/Q3)
PROP: proportion
POP: proportion of level 2 (only binar)
PCI: proportion of level 2, 95% CI
RANGE: range
CV: coefficient of variation
MODE: mode
MISS: number of missing values
PNM: proportion of non missing values
COMB: POP for binar and MQQ for continues
SKEW: skewness
KURT: excess kurtosis
GEO: geometric mean
HARM: harmonic mean
TM1: truncated mean 1%
TM5: truncated mean 5%
TM10: truncated mean 10%
TM25: truncated mean 25%
WM1: winsorized mean 1%
WM5: winsorized mean 5%
WM10: winsorized mean 10%
WM25: winsorized mean 25%
M1SD: mean-SD, mean+SD
M2SD: mean-2SD, mean+2SD
M3SD: mean-3SD, mean+3SD
MM1SD: mean, mean-SD, mean+SD
MM2SD: mean, mean-2SD, mean+2SD
MM3SD: mean, mean-3SD, mean+3SD
NORM50: mean-0.675SD, mean+0.675SD
NORM90: mean-1.645SD, mean+1.645SD
NORM95: mean-1.96SD, mean+1.96SD
NORM99: mean-2.576SD, mean+2.576SD
P1: 1th quantile
P2.5: 2.5th quantile
P5: 5th quantile
P10: 10th quantile
P20: 20th quantile
P25: 25th quantile
P30: 30th quantile
P40: 40th quantile
P50: 50th quantile
P60: 60th quantile
P70: 70th quantile
P75: 75th quantile
P80: 80th quantile
P90: 90th quantile
P95: 95th quantile
P97.5: 97.5th quantile
P99: 99th quantile
Andreas Schulz <[email protected]>
sex <- factor(rbinom(1000, 1, 0.4), labels=c('Men', 'Women')) height <- rnorm(1000, mean=1.66, sd=0.1) height[which(sex=='Men')]<-height[which(sex=='Men')]+0.1 weight <- rnorm(1000, mean=70, sd=5) decades <- rbinom(1000, 3, 0.5) decades <- factor(decades, labels=c('[35,45)','[45,55)','[55,65)','[65,75)')) d<-data.frame(sex, decades, height, weight) tabular.ade(x_vars=c('height', 'weight'), xname=c('Height [m]','Weight [kg]'), y_vars=c('N', 'MEAN', 'SD', 'SKEW', 'KURT'), rows=c('sex', 'ALL', 'decades', 'ALL'), rnames=c('Gender', 'Age decades'), data=d, FUN=stat_cell)
sex <- factor(rbinom(1000, 1, 0.4), labels=c('Men', 'Women')) height <- rnorm(1000, mean=1.66, sd=0.1) height[which(sex=='Men')]<-height[which(sex=='Men')]+0.1 weight <- rnorm(1000, mean=70, sd=5) decades <- rbinom(1000, 3, 0.5) decades <- factor(decades, labels=c('[35,45)','[45,55)','[55,65)','[65,75)')) d<-data.frame(sex, decades, height, weight) tabular.ade(x_vars=c('height', 'weight'), xname=c('Height [m]','Weight [kg]'), y_vars=c('N', 'MEAN', 'SD', 'SKEW', 'KURT'), rows=c('sex', 'ALL', 'decades', 'ALL'), rnames=c('Gender', 'Age decades'), data=d, FUN=stat_cell)
Creates simple to highly customized tables for a wide selection of descriptive statistics, with or without weighting the data.
tabular.ade(x_vars, xname=NULL, y_vars=NULL, yname=NULL, z_vars=NULL, zname=NULL, rows=NULL, rnames=NULL, cols=NULL, cnames=NULL, w=NULL, data=NULL, FUN, allnames=FALSE, nonames=TRUE, alllabel='Total', inset='?', remove='', n_min=0, ...)
tabular.ade(x_vars, xname=NULL, y_vars=NULL, yname=NULL, z_vars=NULL, zname=NULL, rows=NULL, rnames=NULL, cols=NULL, cnames=NULL, w=NULL, data=NULL, FUN, allnames=FALSE, nonames=TRUE, alllabel='Total', inset='?', remove='', n_min=0, ...)
x_vars |
This variable will be used to calculate the statistics for it.
|
xname |
Labels for x.
|
y_vars |
This variable can be used to calculate bivariable statistics.
|
yname |
Labels for y.
|
z_vars |
This variable can be used for additional calculations.
|
zname |
Labels for z.
|
rows |
These factors will be used to separate the rows of the table in subgroups.
|
rnames |
Labels for rows.
|
cols |
These factors will be used to separate the columns of the table in subgroups.
|
cnames |
Labels for cols.
|
w |
This numeric variable will be used to weight the table.
|
data |
A data frame with all used variables. |
FUN |
An abstract cell function to calculate statistics in every cell of the table. See details. |
allnames |
Logical asking whether to fill every cell with labels or only the first one. |
nonames |
Logical asking whether to use dimnames for variable labels or make all labeling in the table self. |
alllabel |
Label for overall group without splitting in this factor. |
inset |
Inset text in each cell, '?' will be replaced with the value of the cell. |
remove |
Remove a character string from each cell. |
n_min |
min N in each cell, it will be only passed in the cell function. But it is necessary to suppress calculation of statistics using only few values. |
... |
additional parameters passed to the FUN |
FUN can be a cell function from this package or a custom cell function.
The custom cell function must take the following parameters, but it is not necessary to use them.
x, The whole x variable.
y, The whole y variable.
z, The whole z variable.
w, The whole w variable.
cell_ids, Index vector to select values that belong in this cell.
row_ids, Index vector to select values that belong in this row.
col_ids, Index vector to select values that belong in this col.
vnames, A vector of length 3, with labels of variables (x,y,z)
vars, A vector of length 3, with names of variables (x,y,z)
n_min , Min needed N for calculation.
... , additional custom parameters.
For an example with simple mean see below.
A character Matrix.(Table)
Andreas Schulz <[email protected]>
# 1) simple own FUN cell function. s_mean<- function(x, y, z, w, cell_ids, row_ids, col_ids, vnames, vars, n_min, ds=3){ out<- '' if(length(cell_ids)>= n_min){ out<- format(mean(x[cell_ids], na.rm=TRUE), digits=ds) } return(out) } ########################################## # 2) simple 2 x 2 table of means sex <- factor(rbinom(5000, 1, 0.5), labels=c('Men', 'Women')) age <- round(runif(5000, 18, 89)) treat <- factor(rbinom(5000, 1, 0.3), labels=c('control', 'treated')) d<-data.frame(sex, age, treat) tabular.ade(x_vars='age', xname='Age [y]', rows='sex', rnames='Sex', cols='treat', cnames='Treatment', data=d, nonames=FALSE, FUN=s_mean) ########################################## # 3) Relative frequency table d$dosis <- round(runif(5000, 0.5, 6.49)) tabular.ade(x_vars='age', xname='Age [y]', rows=c('sex', 'treat'), rnames=c('Sex', 'Treatment'), cols='dosis', cnames='Dosis', data=d, FUN=n_cell, type='pct') ########################################## # 4) Weighted median table d$w <- runif(5000, 0.1, 5) d$bmi <- rnorm(5000, 30, 3) tabular.ade(x_vars=c('age', 'bmi'), xname=c('Age', 'BMI'), cols=c('sex', 'ALL', 'treat'), cnames=c('Sex', 'Treatment'), w='w', data=d, FUN=quantile_cell) ########################################## # 5) Correlation table between age and bmi tabular.ade(x_vars='age', xname='Age', y_vars='bmi', yname='BMI', rows=c('dosis'), rnames=c('Dosis'), cols=c('sex', 'treat'), cnames=c('Sex', 'Treatment'), data=d, FUN=corr_p_cell) ########################################## # 6) Multiple statistics tabular.ade(x_vars=c('N', 'MEAN', 'SD', 'SKEW', 'KURT', 'RANGE'), y_vars=c('age', 'bmi'), yname=c('Age', 'BMI'), cols=c('sex', 'ALL', 'treat'), cnames=c('Sex', 'Treatment'), w='w', data=d, FUN=stat_cell)
# 1) simple own FUN cell function. s_mean<- function(x, y, z, w, cell_ids, row_ids, col_ids, vnames, vars, n_min, ds=3){ out<- '' if(length(cell_ids)>= n_min){ out<- format(mean(x[cell_ids], na.rm=TRUE), digits=ds) } return(out) } ########################################## # 2) simple 2 x 2 table of means sex <- factor(rbinom(5000, 1, 0.5), labels=c('Men', 'Women')) age <- round(runif(5000, 18, 89)) treat <- factor(rbinom(5000, 1, 0.3), labels=c('control', 'treated')) d<-data.frame(sex, age, treat) tabular.ade(x_vars='age', xname='Age [y]', rows='sex', rnames='Sex', cols='treat', cnames='Treatment', data=d, nonames=FALSE, FUN=s_mean) ########################################## # 3) Relative frequency table d$dosis <- round(runif(5000, 0.5, 6.49)) tabular.ade(x_vars='age', xname='Age [y]', rows=c('sex', 'treat'), rnames=c('Sex', 'Treatment'), cols='dosis', cnames='Dosis', data=d, FUN=n_cell, type='pct') ########################################## # 4) Weighted median table d$w <- runif(5000, 0.1, 5) d$bmi <- rnorm(5000, 30, 3) tabular.ade(x_vars=c('age', 'bmi'), xname=c('Age', 'BMI'), cols=c('sex', 'ALL', 'treat'), cnames=c('Sex', 'Treatment'), w='w', data=d, FUN=quantile_cell) ########################################## # 5) Correlation table between age and bmi tabular.ade(x_vars='age', xname='Age', y_vars='bmi', yname='BMI', rows=c('dosis'), rnames=c('Dosis'), cols=c('sex', 'treat'), cnames=c('Sex', 'Treatment'), data=d, FUN=corr_p_cell) ########################################## # 6) Multiple statistics tabular.ade(x_vars=c('N', 'MEAN', 'SD', 'SKEW', 'KURT', 'RANGE'), y_vars=c('age', 'bmi'), yname=c('Age', 'BMI'), cols=c('sex', 'ALL', 'treat'), cnames=c('Sex', 'Treatment'), w='w', data=d, FUN=stat_cell)