Empirical Cumulative Distribution Function

Returns the desired quantiles of quantile regression object such as an extlogF1() or lms.bcn() VGLM object

eCDF.vglm(object, all = FALSE, ...)

Arguments

object

an object such as a vglm object with family function extlogF1 or lms.bcn.

all

Logical. Return all other information? If true, the empirical CDF is returned.

...

additional optional arguments. Currently unused.

Details

This function was specifically written for a vglm object with family function extlogF1 or lms.bcn. It returns the proportion of data lying below each of the fitted quantiles, and optionally the desired quantiles (arguments tau or percentiles / 100 in the family function). The output is coerced to be comparable between family functions by calling the columns by the same names.

Value

A vector with each value lying in (0, 1). If all = TRUE then a 2-column matrix with the second column being the tau values or equivalent.

See also

extlogF1, lms.bcn, vglm.

Examples

fit1 <- vglm(BMI ~ ns(age, 4), extlogF1, data = bmi.nz)  # trace = TRUE
eCDF(fit1)
#> (tau = 0.25)  (tau = 0.5) (tau = 0.75) 
#>    0.2500000    0.5042857    0.7500000 
eCDF(fit1, all = TRUE)
#>        ecdf  tau
#>   0.2500000 0.25
#>   0.5042857 0.50
#>   0.7500000 0.75