Choosing the Right Technique – When to Use?
| Technique | When to Use |
|---|---|
| Huber Regression | – Small to medium-sized outliers in the data. – When a combination of both least-squares and absolute deviation methods is desired – When scaling of input features and target variable is expected |
| RANSAC Regression | – Large outliers in the y direction – Linear and non-linear regression problems – Situations where a subset of data points can be considered as inliers (e.g., photogrammetry) |
| Theil Sen Regression | – Medium-sized outliers in the X direction – Robustness to multivariate outliers |
| Quantile Regression | Predicting an interval instead of a point |
Methods for Dealing with Outliers in Regression Analysis
Outliers are the unusual values in the dataset that abnormally lie outside the overall data pattern. Detecting outliers is one of the most important steps in data preprocessing since it can negatively affect the statistical analysis and the training process of a machine learning algorithm.
In this article, we will explore different methods to deal with outliers in regression analysis.
Table of Content
- Robust Regression Techniques for Outliers
- 1. Huber Regression
- 2. RANSAC Regression
- 3. Theil Sen Regression
- 4. Quantile Regression
- Choosing the Right Technique – When to Use?
Contact Us