18.9. Conjoint Analysis: "What Is the Optimal Mix of Features and Price?"

A difficult time during the development process is the setting of the final product specifications. This consists of deciding which features the new product will include and at what performance level. The conjoint analysis quant tool is excellent for this task. It also helps you to set the price.

NOTE

Conjoint analysis is one of the most sophisticated quantitative market research tools available.

Conjoint analysis is a technique that uncovers how important component parts of the product are to customers by offering many different scenarios and observing what the customer does. In a way, it exemplifies the old saying "you don't know how important something is until it's gone." The first step in conjoint analysis is deciding which features to include in the study. The second step is to decide what performance level will be tested within each feature. Somewhere in the neighborhood of 12-16 total performance levels (added across all the features) is usually the limit of conventional conjoint analysis. After that, the newer and more sophisticated versions of conjoint are required.

After setting the exact features to be tested, an experimental design is chosen from either software or books. Not every possible combination is tested, usually just a carefully chosen subset (so that all the main effects can be estimated). The next step is to gather the data via the Web, in person, by mail, or by telephone. Finally, ...

Get The PDMA Handbook of New Product Development now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.