Mathematics
8 years ago

New method reduces errors in regression models with outliers and heteroscedasticity.

1 view
The Performance of Robust Estimator on Linear Regression Model Having both Continuous and Categorical Variables with Heteroscedastic Errors
Habshah Midi, Bashar A. Talib

Paper Summary

The researchers developed a new method to improve the accuracy of linear regression models when dealing with outliers and varying error variances. By using robust estimates and a reweighted least squares approach, they were able to reduce the impact of outliers and heteroscedasticity in the data. The results showed a significant decrease in the effect of varying error variances, making the model more reliable.

Related papers

Theme background image
Mathematics
8 years ago

New method tackles outliers and non-normal errors in regression models.

Multicollinearity
Statistical Control
System Identification
1 view
Theme background image
Computer Science
8 years ago

Genetic algorithm revolutionizes accurate estimation of cause-effect relationships in data

Multiobjective Optimization
Swarm Intelligence
Genetic Programming
1 view
Theme background image
Mathematics
3 years ago

New method identifies and fixes outliers in data for more accurate results.

Multicollinearity
Regularization Methods
Multivariate Analysis
1 view