Premium
Application of Multivariate Adaptive Regression Splines (MARS) to the Preference Mapping of Cheese Sticks
Author(s) -
Xiong R.,
Meullenet J. F.
Publication year - 2004
Publication title -
journal of food science
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.772
H-Index - 150
eISSN - 1750-3841
pISSN - 0022-1147
DOI - 10.1111/j.1365-2621.2004.tb06353.x
Subject(s) - multivariate adaptive regression splines , mars exploration program , multivariate statistics , piecewise , regression analysis , selection (genetic algorithm) , preference , regression , segmented regression , mathematics , variable (mathematics) , computer science , artificial intelligence , statistics , bayesian multivariate linear regression , biology , mathematical analysis , astrobiology
A novel modeling technique named MARS (Multivariate Adaptive Regression Splines) can automate variable selection as well as model selection. The main purpose of this study was to apply MARS to consumer preference mapping using consumer test data for cheese sticks. The results show that MARS was capable of modeling consumer's preference patterns for cheese sticks. One distinct advantage of MARS in preference mapping is that it has the ability to model hedonic‐scale response variables (such as overall acceptance, acceptance of appearance, flavor, and texture) from “Just About Right” (JAR) predictor variables (such as color, size, saltiness, breading, and cheese texture). In addition, MARS can reveal the underlying relationship between the predictors and the response in a piecewise regression function. This study shows that MARS has potential uncovering underlying patterns hidden in complex data.