MODEL SELECTION VIA ROBUST VERSION OF R-SQUARED

@article{Saleh2014MODELSV,
  title={MODEL SELECTION VIA ROBUST VERSION OF R-SQUARED},
  author={Shokrya Saleh},
  journal={Journal of Mathematics and Statistics},
  year={2014},
  volume={10},
  pages={414-420}
}
  • Shokrya Saleh
  • Published 9 October 2014
  • Mathematics
  • Journal of Mathematics and Statistics
R-squared ( R 2 ) is a popular method for variable selection in lin ear regression models. R 2 based on Least Squares (LS) regression minimizes the sum of the sq uared residuals; LS is sensitive to outlier observation. Alternative criterion based on M-estimators, which is less sensitive to outlying ob servation has been proposed. In this study explicit expression for suc h criterion is obtained when the Least Trimmed Squares (LTS) estimator is used. The influence function of R 2 is also… 
View via Publisher
3 Citations
Background Citations
2
Methods Citations
1

Figures and Tables from this paper

3 Citations

Citation Type

Citation Type

Robust Variable Selection Based on Schwarz Information Criterion for Linear Regression Models
  • Shokrya Saleh
  • Computer Science
    Mathematical Statistician and Engineering Applications
  • 2022
TLDR
The robust properties of SIC derives its influence function and robust SIC based on the MM-estimation scale is proposed, aim to produce criterion which is effective in selecting accurate models in the presence of vertical outliers and high leverage points.
Influence of Risk Mitigation Strategies on Supply Chain Resilience in the Petroleum Industry in Kenya
.......................................................................................................... XIX CHAPTER ONE…
The influence of outsourcing the core deliverables on the business performance at Eskom Distribution South Africa
Submitted in fulfilment of the requirements for Degree of Master of Management Sciences: Business Administration, Durban University of Technology, 2017.

References

SHOWING 1-10 OF 16 REFERENCES
Another Cautionary Note about R 2: Its Use in Weighted Least-Squares Regression Analysis
Abstract A recent article in this journal presented a variety of expressions for the coefficient of determination (R 2) and demonstrated that these expressions were generally not equivalent. The…
Coefficients of determination for least absolute deviation analysis
Cautionary Note about R 2
Abstract The coefficient of determination (R 2) is perhaps the single most extensively used measure of goodness of fit for regression models. It is also widely misused. The primary source of the…
Estimators of the multiple correlation coefficient: Local robustness and confidence intervals
Many robust regression estimators are defined by minimizing a measure of spread of the residuals. An accompanying R2-measure, or multiple correlation coefficient, is then easily obtained. In this…
The coefficient of determination exposed !
The accessibility to computers, especially timesharing varieties, has made regression analysis a frequently used tool for estimating the relationship between an observed response (dependent variable)…
Model Comparisons and R 2
Abstract Much of the confusion surrounding interpretation and application of the coefficient of determination, R 2, can be alleviated if it is defined explicitly as a comparison of a given model to…
Robust statistics: the approach based on influence functions
TLDR
This paper presents a meta-modelling framework for estimating the values of Covariance Matrices and Multivariate Location using one-Dimensional and Multidimensional Estimators.
HIGH BREAKDOWN-POINT AND HIGH EFFICIENCY ROBUST ESTIMATES FOR REGRESSION
On introduit une classe d'estimateurs robustes pour le modele lineaire, appeles estimateurs MM, et definis par une procedure en trois etapes
Robust regression and outlier detection
TLDR
This paper presents the results of a two-year study of the statistical treatment of outliers in the context of one-Dimensional Location and its applications to discrete-time reinforcement learning.
Influence in canonical correlation analysis
The perturbation theory of the generalized eigenproblem is used to derive influence functions of each squared canonical correlation coefficient and the corresponding canonical vector pair. Three…
...
...