How to interpret partworth utilities

Partworth utilities (also know as attribute importance scores and level values) are numerical scores that measure how much each attribute and level influenced the customer’s decision to make that choice. Because attribute and level partworths are interrelated, in this post we will look at them using the same example of tissue paper. Suppose the company wants to find out customers’ preferences for tissue paper to re-assess its product range, as a pathway to growth. The charts below show some common attributes of the company’s (and competitors’) tissue paper:

  • Texture: weave-like or simple
  • Ply: 3 ply or 2 ply
  • Scent and colour: “recycled unscented”, “white unscented”, or “white scented”
  • Price per 100 sheets: 30¢, 55¢, or 70¢

In this example, “Texture”, “Ply”, “Scent and colour”, and “Price per 100 sheets” are attributes. “3 ply” and “2 ply” are levels of the attribute “ply”. (You can read more about specification of attributes and levels here).

Relative importance by attribute (attribute partworths)

The index attached to each attribute shows its importance relative to others. At 48%, the “scent and colour” attribute turns out to be the most important with “ply” being the least important attribute. It appears price is not as important a factor as “scent and colour”.

This chart shows how strongly the variations of attributes affect customers’ choice, but only for the levels that you chose in the design. If a more extreme level were added to one of the attributes, that attribute would likely become higher in importance. For example, if we add a more extreme price level ($1.50), customers are likely to shun it and therefore the partworth of that level will be very negative, which will in turn inflate importance of the whole price attribute.

Relative value by level (level partworths)

Level partworths allow you to dive deeper to understand what specific features within an attribute drive customers’ choice. In this example, recycled unscented tissue paper is strongly preferred to white scented and somewhat to white unscented.

Levels that are strongly preferred by customers are assigned higher scores, levels that perform poorly (in comparison) are assigned lower scores. The chart is scaled so that, for each attribute, the sum of all positive values equals (the absolute value of) the sum of all negative values.

Again, it is important to remember that these partworths are relative. If we include “black with velvet scent” as another level for the attribute “scent and colour”, the relative value of each level will change.

Preference for “None of the above” option

Segmentation reports provide another useful metric: Preference for the “None of the above” option. While conjoint studies generally cannot precisely estimate the share of people who would or would not buy in a product category (hence it is a good idea to have a couple of screening questions upfront), they do provide a glimpse of that if you include the “None of the above” option (which is enabled by default). This can be especially helpful in comparing segments.

For example, in the table below, Segment 2 appears a little more likely to buy choose “None of the above”. Hence, it is perhaps best to give a higher weight to the answers of Segment 1.

Attribute Level Segment 1 Segment 2 Market overall
Texture Weave-like texture
Simple texture
Ply 3 ply
2 ply
Scent and colour Recycled unscented
White unscented
White scented
Price per 100 sheets $1.99
Preference for "None of the above" option
Size of segment 67% 33% 100%