Maximum Difference Scaling (MaxDiff) obtains preference/importance scores for multiple items (brand preferences, product offers, etc.). The MaxDiff procedure requires respondents to select the most and least important concepts or features from pairs of concepts or features. This also provides insights into market segment prioritization.
Based on the same tradeoff evaluation methods as conjoint analysis, MaxDiff is designed to efficiently measure the relative importance of a large number of attributes. It is applicable to a wide variety of research situations including identifying the best technical solutions.
In comparison to typical rating scales, MaxDiff scores demonstrate greater discrimination among items and between respondents of the items. In addition, since respondents make choices rather than expressing strength of preference using some numeric scale, there is no opportunity for scale use bias.
This approach yields a more effective evaluation of concepts or features than rating each concept or feature individually, and provides improved discrimination between concepts or features.
Respondents are shown a set of the possible items in the exercise, and are asked to indicate the most and least important. Respondents typically complete a dozen or more such sets where each set contains a different subset of items.
MaxDiff scaling results in a point allocation rating for each concept or feature that describes its attractiveness compared to all other concepts or offerings. In the analysis, a total of 100 points is allocated among the concepts or features to show their relative attractiveness. A concept or feature that receives 10 points is twice as attractive as a concept or feature that receives 5 points half as attractive as a concept or feature that receives 20 points.