Bias removal in new-product tests; MARG Bangalore

Abstract

The purpose of this project was to develop a technique or a set of tools that would make the analytical results of new-product tests more reliable and meaningful. More specifically, the objectives were: * to eliminate redundant attributes, * to identify any kind of significant attribute clubbing, and * to eliminate bias of any form found in the data. Secondary data from a previous new-product test of the monadic-aggregate form was used in the study. The names of the project or the samples used are deliberately withheld. In order to identify the various kinds of data structures and to eliminate biases, the following types of analyses were used * factor analysis * discriminant analysis * correlation and multiple regression analyses * tests of significance of means and Analysis of Variance * JP Guilford’s bias-removal technique.