Mid-distribution Functions

Compute mid-cumulative probabilities and mid-quantiles

Usage

midecdf(x, na.rm = FALSE)
midquantile(x, probs = 1:3/4, na.rm = FALSE)

Arguments

x

numeric vector of observations used to estimate the mid-cumulative distribution or the mid-quantiles.

probs

numeric vector of probabilities with values in [0,1].

na.rm

logical value indicating whether NA values should be stripped before the computation proceeds.

Value

An object of class class midecdf or midquantile with mid-cumulative probabilities and mid-quantiles. For midecdf, this is a list that contains:

x

unique values of the vector x at which mid-cumulative probabilities are calculated.

y

estimated mid-cumulative probabilities.

fn

interpolating function of the points (x,y).

data

input values.

For midquantile, this is a list that contains:

x

probabilities probs at which mid-quantiles are calculated.

y

estimated mid-cumulative probabilities.

fn

interpolating function of the points (x,y).

data

input values.

References

Ma Y., Genton M., and Parzen E. Asymptotic properties of sample quantiles of discrete distributions. Annals of the Institute of Statistical Mathematics 2011;63(2):227-243

Parzen E. Quantile probability and statistical data modeling. Statistical Science 2004;19(4):652-62.

Author

Marco Geraci

See also

confint.midquantile, plot.midquantile

Examples

x <- rpois(100, lambda = 3)
midquantile(x)
#> Empirical mid-quantile function 
#> Call:
#> midquantile(x = x)
#>