A New Approach to Robust Partial Least Squares Regression Analysis
Journal Title: INTERNATIONAL JOURNAL OF MATHEMATICS TRENDS AND TECHNOLOGY - Year 2014, Vol 9, Issue 3
Abstract
Partial Least Squares Regression (PLSR) is a linear regression technique developed to relate many independent variables to one or several dependent variables. Robust methods are introduced to reduce or remove the effects of outlying data points. In the previous studies in robust PLSR field it has been mentioned that if the sample covariance matrix is properly robustified further robustification of the linear regression steps of the PLS1 algorithm (PLSR with univariate dependent variable) becomes unnecessary. Therefore, the purpose of this study is to propose a new approach to robust PLSR based on statistical procedures for covariance matrix robustification by selecting the well-known S-estimators. Both simulation results and an analysis on a real data set, which is used in robust PLSR literature frequently, showing the effectiveness, success in fitting to regular data points and predictive power of the new proposed robust PLSR method.
Authors and Affiliations
Esra Polat , Suleyman Gunay
Keywords
Related Articles
- EP ID EP152632
- DOI -
- Views 265
- Downloads 0
Numerical Comparison of multi-step iterative methods for finding roots of nonlinear equations
—In this paper, we compare different multi-step Newton like methods for solving nonlinear equations. Results are shown in form of iteration tables. Numerical results show that the Modified Shamanskii...
Innovation-Driven Sustainability Modelling for Poverty Alleviation Initiatives in Rural India: A Mathematical Approach
Today’s world is facing many severe challenges even though it had made encouraging progresses in economic and other respects. Agriculture is one of the important sources of economic and social growth of our country. In t...
On Hilbert-Schmidt Tuples of Commutative Bounded Linear Operators on Separable Banach Spaces
In this paper, we will study some properties of Tuples that there components are commutative bounded linear operators on a separable Hilbert space H, then we will develop those properties for infinity-Tuples and find som...
Appell Transforms Associated With Expansions in Terms of Generalized Heat Polynomials
In this paper we have discussed the regions of convergence of the series Σ∞n=0 anpn,α,β and Σ∞n=0 bn Wn,α,β (x1t).We have also discussed the class H*of generalized temperature functions having the Huygens property. Final...
Location of Regions Containing No Zero of a Polynomial
In this paper we locate regions containing no zero of a polynomial whose coefficients are restricted to certain conditions