outliers (version 0.15)

scores: Calculate scores of the sample

Description

This function calculates normal, t, chi-squared, IQR and MAD scores of given data.

Usage

scores(x, type = c("z", "t", "chisq", "iqr", "mad"), prob = NA, lim = NA)

Arguments

x

a vector of data.

type

"z" calculates normal scores (differences between each value and the mean divided by sd), "t" calculates t-Student scores (transformed by (z*sqrt(n-2))/sqrt(z-1-t^2) formula, "chisq" gives chi-squared scores (squares of differences between values and mean divided by variance. For the "iqr" type, all values lower than first and greater than third quartile is considered, and difference between them and nearest quartile divided by IQR are calculated. For the values between these quartiles, scores are always equal to zero. "mad" gives differences between each value and median, divided by median absolute deviation.

prob

If set, the corresponding p-values instead of scores are given. If value is set to 1, p-value are returned. Otherwise, a logical vector is formed, indicating which values are exceeding specified probability. In "z" and "mad" types, there is also possibility to set this value to zero, and then scores are confirmed to (n-1)/sqrt(n) value, according to Shiffler (1998). The "iqr" type does not support probabilities, but "lim" value can be specified.

lim

This value can be set for "iqr" type of scores, to form logical vector, which values has this limit exceeded.

Value

A vector of scores, probabilities, or logical vector.

References

Schiffler, R.E (1998). Maximum Z scores and outliers. Am. Stat. 42, 1, 79-80.

See Also

mad, IQR, grubbs.test,

Examples

# NOT RUN {
set.seed(1234)
x = rnorm(10)
scores(x)
scores(x,prob=1)
scores(x,prob=0.5)
scores(x,prob=0.1)
scores(x,prob=0.93)
scores(x,type="iqr")
scores(x,type="mad")
scores(x,prob=0)
# }