Descriptive statistics for continuous variables, with the option of stratifying by a categorical variable.
proc_means(df, vars = NULL, var_order = NULL, by = NULL, n = T,
mean = TRUE, sd = TRUE, min = TRUE, max = TRUE, median = FALSE,
q1 = FALSE, q3 = FALSE, iqr = FALSE, nmiss = FALSE,
nobs = FALSE, p = FALSE, p_round = 4, display_round = 3)
A data.frame with columns variable, by
variable, and
a column for each summary statistic.
A data frame or tibble.
Character vector of numeric variables to generate descriptive
statistics for. If the default (NULL
), all variables are included,
except for any specified in by
.
Character vector listing the variable names in the order
results should be displayed. If the default (NULL
), variables are
displayed in the order specified in vars
.
Discrete variable. Separate statistics will be produced for
each level. Default NULL
provides statistics for all observations.
logical. Display number of rows with values. Default TRUE
.
logical. Display mean value. Default TRUE
.
logical. Display standard deviation. Default TRUE
.
logical. Display minimum value. Default TRUE
.
logical. Display maximum value. Default TRUE
.
logical. Display median value. Default FALSE
.
logical. Display first quartile value. Default FALSE
.
logical. Display third quartile value. Default FALSE
.
logical. Display interquartile range. Default FALSE
.
logical. Display number of missing values. Default FALSE
.
logical. Display total number of rows. Default FALSE
.
logical. Calculate p-value across by
groups using aov
.
Ignored if no by
variable specified. Default FALSE
.
Number of decimal places p-values should be rounded to.
Number of decimal places displayed values should be rounded to
proc_means(iris, vars = c("Sepal.Length", "Sepal.Width"))
proc_means(iris, by = "Species")
Run the code above in your browser using DataLab