MedianAbsoluteErrorMetric<T>

Models & Types · AiDotNet.Evaluation.Metrics.Regression

Computes Median Absolute Error (MedAE): the median of all absolute errors.

Implements: IRegressionMetric<T>

For Beginners

Median Absolute Error is even more robust to outliers than MAE:

  • Uses the median instead of mean, so outliers have minimal impact
  • Represents the “typical” error - half your predictions are better, half are worse
  • Particularly useful when your data has heavy-tailed error distributions

Compare MedAE vs MAE: if MedAE is much smaller than MAE, you have outlier issues.

How It Works

MedAE = median(|y_i - ŷ_i|)

Constructors

Constructor Summary
MedianAbsoluteErrorMetric()

Properties

Property Summary
MetricDirection Direction { get; }
T MaxValue { get; }
T MinValue { get; }
bool RequiresProbabilities { get; }
bool SupportsMultiClass { get; }
string Category { get; }
string Description { get; }
string Name { get; }

Methods

Method Summary
MetricWithCI<T> ComputeWithCI(ReadOnlySpan<T> predictions, ReadOnlySpan<T> actuals, ConfidenceIntervalMethod ciMethod, double confidenceLevel, int bootstrapSamples, int? randomSeed)
T Compute(ReadOnlySpan<T> predictions, ReadOnlySpan<T> actuals)