MaxDiff, also known as Best-Worst Scaling, is a really useful method, whereby consumers select their most and least liked products from a subset of products. The subset then changes and the task repeats a number of times, according to a statistical design. At Qi, we’ve developed our own software to design a MaxDiff experiment and comprehensively analyse the data. The analyses allows you to report results at the aggregate and individual level. This means that not only will you find which product is most liked and in what order preference lies, but also see individual differences between consumers. The latter leads nicely to cluster analysis.