Skip to contents

Calculates the mean squared error (MSE).

The MSE is defined by $$\frac{1}{n} \sum ((t - \hat{t})^2)$$ where \(t\) is the true value and \(\hat{t}\) is the prediction.

Censored observations in the test set are ignored.

Dictionary

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

MeasureSurvMSE$new()
mlr_measures$get("surv.mse")
msr("surv.mse")

Parameters

IdTypeDefaultLevels
selogicalFALSETRUE, FALSE

Meta Information

  • Type: "surv"

  • Range: \([0, \infty)\)

  • Minimize: TRUE

  • Required prediction: response

Parameter details

  • se (logical(1))
    If TRUE then returns standard error of the measure otherwise returns the mean across all individual scores, e.g. the mean of the per observation scores. Default is FALSE (returns the mean).

Super classes

mlr3::Measure -> mlr3proba::MeasureSurv -> MeasureSurvMSE

Methods

Inherited methods


Method new()

Creates a new instance of this R6 class.

Usage


Method clone()

The objects of this class are cloneable with this method.

Usage

MeasureSurvMSE$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.