Mathematics
8 years ago

New Regression Method Outperforms Traditional Approach in Handling Outliers

2 views
American journal of mathematics and statistics
A Comparion of Ordinary Least Squares Regression and Least Squares Ratio via Generated Data
Öznur İŞÇİ GÜNERİ, Atila Göktaş

Paper Summary

Regression Analysis is a common tool for understanding relationships between variables. Ordinary Least Squares (OLS) is a basic method used in regression analysis. A new method called Least Squares Ratio (LSR) was compared to OLS in terms of accuracy in estimating parameters. The study found that LSR outperformed OLS when dealing with outliers, regardless of sample size.

Related papers

Theme background image
Mathematics
8 years ago

Weighted least squares ratio method improves accuracy in regression analysis with outliers.

Multicollinearity
Chemometrics
System Identification
2 views
Decision Sciences
8 years ago

Outlier detection boosts accuracy of predictive models in statistical regression.

Grey System Theory
Control Systems
Process Fault Detection
1 view
Theme background image
Engineering
8 years ago

New Regression Method Reduces Errors and Increases Stability in Data Analysis

Optoelectronic Systems
Remote Sensing
Control Systems