Conservative-Z CI

The conservative-z confidence intervals based on the ResamplingPairedSubsampling. Because the variance estimate is obtained using only n / 2 observations, it tends to be conservative. This inference method can also be applied to non-decomposable losses.

Point Estimation

For the point estimation, only the first repeats_out resampling iterations will be used, as the other resampling iterations are only used to estimate the variance. This is respected when calling $aggregate() using a standard (non-CI) measure.

Parameters

Only those from MeasureAbstractCi.

References

Nadeau, Claude, Bengio, Yoshua (1999). “Inference for the generalization error.” Advances in neural information processing systems, 12.

Super classes

mlr3::Measure -> mlr3inferr::MeasureAbstractCi -> MeasureCiConZ

Methods

Public methods

• MeasureCiConZ$new()

• MeasureCiConZ$clone()

Inherited methods

• mlr3::Measure$format()
• mlr3::Measure$help()
• mlr3::Measure$print()
• mlr3::Measure$score()
• mlr3inferr::MeasureAbstractCi$aggregate()

---

Method new()

Creates a new instance of this R6 class.

Usage

MeasureCiConZ$new(measure)

Arguments

measure

(Measure or character(1))
A measure of ID of a measure.

---

Method clone()

The objects of this class are cloneable with this method.

Usage

MeasureCiConZ$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.

Examples

ci_conz = msr("ci.con_z", "classif.acc")
ci_conz
#> 
#> ── <MeasureCiConZ> (classif.acc): Conservative-Z Interval ──────────────────────
#> • Packages: mlr3, mlr3measures, and mlr3inferr
#> • Range: [0, 1]
#> • Minimize: FALSE
#> • Average: custom
#> • Parameters: alpha=0.05, within_range=TRUE
#> • Properties: primary_iters
#> • Predict type: response
#> • Predict sets: test
#> • Aggregator: mean()