kurt {fungible} | R Documentation |
Calculate Univariate Kurtosis for a Vector or Matrix
Description
Calculate univariate kurtosis for a vector or matrix (algorithm G2 in Joanes & Gill, 1998). Note that, as defined in this function, the expected kurtosis of a normally distributed variable is 0 (i.e., not 3).
Usage
kurt(x)
Arguments
x |
Either a vector or matrix of numeric values. |
Value
Kurtosis for each column in x. |
Author(s)
Niels Waller
References
Joanes, D. N. & Gill, C. A. (1998). Comparing measures of sample skewness and kurtosis. The Statistician, 47, 183-189.
See Also
Examples
x <- matrix(rnorm(1000), 100, 10)
print(kurt(x))
[Package fungible version 2.4.4 Index]