HuberizedDistribution: Distribution Huberization Wrapper

In distr6: The Complete R6 Probability Distributions Interface

Distribution Huberization Wrapper

Description

A wrapper for huberizing any probability distribution at given limits.

Details

The pdf and cdf of the distribution are required for this wrapper, if unavailable decorate with FunctionImputation first.

Huberizes a distribution at lower and upper limits, using the formula

f_H(x) = F(x), if x ≤ lower

f_H(x) = f(x), if lower < x < upper

f_H(x) = F(x), if x ≥ upper

where f_H is the pdf of the truncated distribution H = Huberize(X, lower, upper) and f_X/F_X is the pdf/cdf of the original distribution.

Super classes

distr6::Distribution -> distr6::DistributionWrapper -> HuberizedDistribution

Active bindings

properties

Returns distribution properties, including skewness type and symmetry.

Methods

Public methods

• HuberizedDistribution$new()

• HuberizedDistribution$clone()

Inherited methods

• distr6::Distribution$cdf()

• distr6::Distribution$confidence()

• distr6::Distribution$correlation()

• distr6::Distribution$getParameterValue()

• distr6::Distribution$iqr()

• distr6::Distribution$liesInSupport()

• distr6::Distribution$liesInType()

• distr6::Distribution$median()

• distr6::Distribution$parameters()

• distr6::Distribution$pdf()

• distr6::Distribution$prec()

• distr6::Distribution$print()

• distr6::Distribution$quantile()

• distr6::Distribution$rand()

• distr6::Distribution$setParameterValue()

• distr6::Distribution$stdev()

• distr6::Distribution$strprint()

• distr6::Distribution$summary()

• distr6::Distribution$workingSupport()

• distr6::DistributionWrapper$wrappedModels()

---

Method new()

Creates a new instance of this R6 class.

Usage

HuberizedDistribution$new(distribution, lower = NULL, upper = NULL)

Arguments

distribution

([Distribution])
Distribution to wrap.

lower

(numeric(1))
Lower limit to huberize the distribution at. If NULL then the lower bound of the Distribution is used.

upper

(numeric(1))
Upper limit to huberize the distribution at. If NULL then the upper bound of the Distribution is used.

Examples

HuberizedDistribution$new(
  Binomial$new(prob = 0.5, size = 10),
  lower = 2, upper = 4
)

# alternate constructor
huberize(Binomial$new(), lower = 2, upper = 4)

---

Method clone()

The objects of this class are cloneable with this method.

Usage

HuberizedDistribution$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.

See Also

Other wrappers: Convolution, DistributionWrapper, MixtureDistribution, ProductDistribution, TruncatedDistribution, VectorDistribution

Examples

## ------------------------------------------------
## Method `HuberizedDistribution$new`
## ------------------------------------------------

HuberizedDistribution$new(
  Binomial$new(prob = 0.5, size = 10),
  lower = 2, upper = 4
)

# alternate constructor
huberize(Binomial$new(), lower = 2, upper = 4)

distr6 documentation built on March 28, 2022, 1:05 a.m.