Search⌘ K
AI Features
Home
Courses
An Introductory Guide to Data Science and Machine Learning

Model Evaluation Measures: Median Absolute Error, and R^2 Score

Explore the use of median absolute error and R squared score as key metrics to evaluate regression models. Understand how median absolute error measures prediction accuracy robust to outliers and how R squared indicates the proportion of variance explained by a model. Gain skills to interpret these metrics and apply them effectively in machine learning projects.

We'll cover the following...

Median absolute error

Median is a descriptive statistics measure and is robust to outliers in the dataset. The rate of error is calculated by taking the median of all absolute differences between the target and the prediction. Lower values mean the model is more accurate.

Formula

If y^\hat{y} is the predicted target real-valued output, then yy is the corresponding target real-valued output and mm is the total number of instances. Then the median absolute error is calculated as follows:

MedAE(y^,y)=median(∣y^1−y1∣,...,∣y^m−ym∣)MedAE(\hat{y}, y) = median(|\hat{y}^1 - y^1|,...,|\hat{y}^m - y^m|) ...