Evaluation values on a Kansei word are assigned to y (dependent) variable and design elements are assigned to x (independent) variables with dummy variables. In QT 1; the qualitative variable such as product body color is called â€śitemâ€ť. The variations of the item such like white / blue / red are called â€ścategoriesâ€ť. Categories are expressed with dummy variables those have 1/0 value. Weights to the categories will be found with a multiple regression model. Computing method is solving (number of all categories â€“ 1) simultaneous equations (Hayashi; 1952).
QT 1 is deterministic because it is a variation of multiple regression model and its solving method uses least square method. Although QT1 is widely used; there are two defects: 1. Problem of sample size; QT1 incorporates (number of category â€“ 1) dummy variables. In multiple regression model; simultaneous equations could not solved when number of variables exceed to the number of samples. Kansei engineering situation has tens of samples; and many cases have the larger number of design variables. Then; the analyst has to divide design variables to do analysis. 2. Problem of interactions between x variables; If there are heavy interactions between x variables; analyzing result is distorted. The problem is known as a multicollinearity in multiple regression analysis.
PLS (Partial Least Squares) is becoming popular in chemometrics. PLS has possibility to resolve above problems. In this study we analyze personal garden Kansei engineering experiment data with PLS; and consider its analyzing ability.
In this paper; we present considerations on analysis ability of PLS with Kansei evaluation data of personal gardens.
Keywords: Partial Least Squares; Kansei analysis; Multivariate analysis; Garden design