descr: Descriptive statistics for one or several variables

In eatTools: Miscellaneous Functions for the Analysis of Educational Assessments

Descriptive statistics for one or several variables

Description

Function computes descriptive statistics for one variable or several variables within a data frame.

Usage

descr (variable, na = NA, p.weights = NULL, na.rm = FALSE, verbose=TRUE) 

Arguments

variable	one variable or a data.frame with several variables
na	optional values with should be considered a missing values
p.weights	optional: vector with individual weights if weighted statistics should be computed
na.rm	logical: should missings be removed prior to estimation?
verbose	logical: Print messages to console?

Value

a data frame with the following columns

N	number of observations
N.valid	number of non-missing observations
Missing	number of missings
Minimum	minimum of numeric variables
Maximum	maximum of numeric variables
Sum	sum of numeric variables
Mean	arithmetic mean of numeric variables
std.err	standard error of the arithmetic mean. Note: for weighted means, standard error is estimated according to Cochran (1977): sigma_x^2=n/((n-1)*w_s^2)*Sigma(w_i^2*(x_i-x)).
sig	p value
Median	median of numeric variables
SD	standard deviation of numeric variables
Var	variance of numeric variables

Author(s)

Sebastian Weirich

References

Cochran W. G. (1977). Sampling Techniques (3rd Edn). Wiley, New York

Examples

data(mtcars)
descr(mtcars)

eatTools documentation built on Oct. 12, 2024, 1:06 a.m.