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

Sequences of Special Dio - Triples

This paper concerns with the study of constructing sequences of special Dio-Triples (a,b,c) such that the product of any two elements of the set added with their sum and increased by a non-zero integer or a polynomial wi...

Pathos Vertex Semientire Block Graph

The pathos vertex semientire block graph denoted by Pvb(G) is the graph whose vertex set is V(T) bi r and the two vertices are adjacent if and only if they are adjacent vertices, vertices lie on the blocks, vertices lie...

A Study of an Inflationary Inventory Model with Stock-Dependent Demand and Shortages

An inventory replenishment problem for a deteriorating item is considered over a finite time-horizon with shortages in all cycles and stock-dependent demand rate. The effects of inflation and time-value of money are also...

Student Perceptions of Online Homework in Preparatory Year Pre-Calculus courses

The Internet is gradually becoming part and parcel of our lives. As a result, online educational technologies are gaining more acceptance in our educational system. This is more so in higher education. However, online as...

Total Outer Equitable Connected Domination of a Graph

Let G = (V, E) be a graph. A set D V (G) is equitable dominating set of G if v V – D a vertex u D such that uv E (G) and |d(u) – d(v)| 1. A set D V (G) is outer equitable dominating set if D is equitable dominati...

Download PDF file
  • EP ID EP152632
  • DOI -
  • Views 240
  • Downloads 0

How To Cite

Esra Polat, Suleyman Gunay (2014). A New Approach to Robust Partial Least Squares Regression Analysis. INTERNATIONAL JOURNAL OF MATHEMATICS TRENDS AND TECHNOLOGY, 9(3), 197-205. https://europub.co.uk/articles/-A-152632