Learn R Programming
mlr3proba (version 0.2.1)

mlr_measures_surv.cindex: Concordance Statistics Survival Measure

Description

Calculates weighted concordance statistics, which, depending on the chosen weighting method and tied times solution, are equivalent to several proposed methods.

For the Kaplan-Meier estimate of the training survival distribution, S, and the Kaplan-Meier estimate of the training censoring distribution, G:

weight_meth:

  • "I" = No weighting. (Harrell)

  • "GH" = Gonen and Heller's Concordance Index

  • "G" = Weights concordance by G^-1.

  • "G2" = Weights concordance by G^-2. (Uno et al.)

  • "SG" = Weights concordance by S/G (Shemper et al.)

  • "S" = Weights concordance by S (Peto and Peto)

The last three require training data.

Arguments

Dictionary

This Measure can be instantiated via the dictionary mlr_measures or with the associated sugar function msr():

MeasureSurvCindex$new()
mlr_measures$get("surv.cindex")
msr("surv.cindex")

Meta Information

  • Type: "surv"

  • Range: \([0, 1]\)

  • Minimize: FALSE

  • Required prediction: crank

Super classes

mlr3::Measure -> mlr3proba::MeasureSurv -> MeasureSurvCindex

Active bindings

cutoff

(numeric(1)) Cut-off time to evaluate concordance up to.

weight_meth

(numeric(1)) Method for weighting concordance.

tiex

(numeric(1)) Cut-off time to evaluate concordance up to.

Methods

Public methods

Method new()

This is an abstract class that should not be constructed directly.

Usage

MeasureSurvCindex$new(
  cutoff = NULL,
  weight_meth = c("I", "G", "G2", "SG", "S", "GH"),
  tiex = 0.5
)

Arguments

cutoff

(numeric(1)) Cut-off time to evaluate concordance up to.

weight_meth

(character(1)) Method for weighting concordance. Default "I" is Harrell's C. See details.

tiex

(numeric(1)) Weighting applied to tied rankings, default is to give them half weighting.

Method clone()

The objects of this class are cloneable with this method.

Usage

MeasureSurvCindex$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.

References

mlr3probapeto_1972

mlr3probaharrell_1982

mlr3probagoenen_2005

mlr3probaschemper_2009

mlr3probauno_2011

See Also

Other survival measures: mlr_measures_surv.beggC, mlr_measures_surv.calib_alpha, mlr_measures_surv.calib_beta, mlr_measures_surv.chambless_auc, mlr_measures_surv.gonenC, mlr_measures_surv.grafSE, mlr_measures_surv.graf, mlr_measures_surv.harrellC, mlr_measures_surv.hung_auc, mlr_measures_surv.intloglossSE, mlr_measures_surv.intlogloss, mlr_measures_surv.loglossSE, mlr_measures_surv.logloss, mlr_measures_surv.maeSE, mlr_measures_surv.mae, mlr_measures_surv.mseSE, mlr_measures_surv.mse, mlr_measures_surv.nagelk_r2, mlr_measures_surv.oquigley_r2, mlr_measures_surv.rmseSE, mlr_measures_surv.rmse, mlr_measures_surv.schmid, mlr_measures_surv.song_auc, mlr_measures_surv.song_tnr, mlr_measures_surv.song_tpr, mlr_measures_surv.unoC, mlr_measures_surv.uno_auc, mlr_measures_surv.uno_tnr, mlr_measures_surv.uno_tpr, mlr_measures_surv.xu_r2