Mathematical Psychology
Psychometrics & MeasurementDavid KrantzPatrick SuppesFrederic Lord
About
HomeDecision MakingMulti-Alternative Choice
Multi-Alternative Choice

Best-Worst Scaling

Best-Worst Scaling asks respondents to identify the best and worst options in subsets of items, providing more information per question than simple ranking and yielding interval-scale measurements.

Best-Worst Scaling (BWS), also called maximum difference scaling, was introduced by Jordan Louviere in 1987 and developed with Anthony Marley and colleagues. Rather than rating items on a scale or making pairwise comparisons, respondents identify the best and worst items in a subset. This yields more discriminating data than simple ratings and avoids many response biases.

Three Cases of BWS

BWS Case Types Case 1 (object): best/worst items from a set → item scale values
Case 2 (profile): best/worst attributes of a product profile → attribute importance
Case 3 (multi-profile): best/worst profiles from a set → preference model

In Case 1 BWS, each respondent sees a subset (typically 4–5) of items and selects the best and worst. Across many subsets (designed using balanced incomplete block designs), the frequency of being chosen as best vs. worst provides an interval-scale value for each item. The data are typically analyzed using multinomial logit models, linking BWS to Thurstonian scaling and Luce's choice axiom.

Advantages

BWS provides more information per task than paired comparisons (which yield only one comparison per question) and avoids scale-use biases that plague Likert-type ratings. It has been widely applied in health economics (valuing health states), marketing (preference measurement), environmental economics (valuing ecosystem services), and cross-cultural research where response style differences make ratings problematic.

Related Topics

FoundationsPaired ComparisonsFoundationsThurstonian ScalingDecision MakingMultinomial Logit

References

  1. Finn, A., & Louviere, J. J. (1992). Determining the appropriate response to evidence of public concern: The case of food safety. Journal of Public Policy & Marketing, 11(2), 12–25. https://doi.org/10.1177/074391569201100202
  2. Marley, A. A. J., & Louviere, J. J. (2005). Some probabilistic models of best, worst, and best–worst choices. Journal of Mathematical Psychology, 49(6), 464–480. https://doi.org/10.1016/j.jmp.2005.05.003
  3. Louviere, J. J., Flynn, T. N., & Marley, A. A. J. (2015). Best-Worst Scaling: Theory, Methods and Applications. Cambridge University Press. https://doi.org/10.1017/CBO9781107337855

External Links