Nonmetric Unfolding of Marketing Data: Degeneracy and Stability

Nonmetric unfolding is a powerful (nonparametric) analytical tool generating a preference-based joint display of subjects (e.g., customers) and objects (e.g., brands or products). Systematic patterns in customers’ preferences can be directly inferred from this display, and may provide valuable input for making important marketing decisions such as deciding what new product to launch. Unfortunately, nonmetric unfolding frequently produces degenerate unfolding solutions (i.e., unfolding solutions showing close-to-perfect model fit irrespective of the data analyzed). As a degenerated display shows ill-positioned customers and brands/products, the chance of making an incorrect marketing decision (e.g., launching the wrong product) is very high. To solve this problem adequately, we combine bootstrapping with penalized nonmetric unfolding (Prefscal) to obtain an accurate, nondegenerate and stable unfolding solution.