TY - JOUR T1 - Partial Least Squares Regression TT - رگرسیون کم‌ترین توان‌های دوم JF - srtc-ijoss JO - srtc-ijoss VL - 20 IS - 2 UR - http://ijoss.srtc.ac.ir/article-1-79-en.html Y1 - 2010 SP - 289 EP - 304 KW - Cross validation KW - prediction KW - multicollinearity KW - component KW - PLS N2 -  In different researches, we deal with problems that need to predict the behavior of a response variable by a set of explanatory variables. Multiple regression is one of the statistical methods that is widely used in these type of situations. When there is a linear relation between explanatory variables we will faced with multi-collinearity problem that causes ordinary least squares estimators of regression coefficients not to be robust. Partial least squares regression is a multivariate method that used when there is high collinearity between explanatory variables. In this paper, this method is introduced. M3 ER -