What is conjoint analysis?

Sawtooth Software, 2021

Introduction to conjoint analysis

Conjoint analysis is the premier approach for optimizing product features and pricing. It mimics the trade-offs people make in the real world when making choices. In conjoint analysis surveys you offer your respondents multiple alternatives with differing features and ask which they would choose.

With the resulting data, you can predict how people would react to any number of product designs and prices. Because of this, conjoint analysis is used as the advanced tool for testing multiple features at one time when A/B testing just doesn’t cut it.

Conjoint analysis is commonly used for:

Designing and pricing products / Healthcare and medical decisions / Branding, package design, and product claims / Environmental impact studies / Needs-based market segmentation

How does conjoint analysis work?

• Step 1: Break products into attributes and levels

In the picture below, a conjoint analysis example, the attributes of a car are broken down into brand, engine, type, and price. Each of those attributes has different levels. 

Rather than directly ask survey respondents what they prefer in a product, or what attributes they find most important, conjoint analysis employs the more realistic context of asking respondents to evaluate potential product profiles (see below).

Step 2: Show product profiles to respondents

Each profile includes multiple conjoined product features (hence, conjoint analysis), such as price, size, and color, each with multiple levels, such as small, medium, and large.

In a conjoint exercise, respondents usually complete between 8 to 20 conjoint questions. The questions are designed carefully, using experimental design principles of independence and balance of the features.

Step 3: Quantify your market’s preferences and create a model

By independently varying the features that are shown to the respondents and observing the responses to the product profiles, the analyst can statistically deduce what product features are most desired and which attributes have the most impact on choice (see below).

In contrast to simpler survey research methods that directly ask respondents what they prefer or the importance of each attribute, these preferences are derived from these relatively realistic trade-off situations.

The result is usually a full set of preference scores (often called part-worth utilities) for each attribute level included in the study. The many reporting options allow you to see which segments (or even individual respondents) are most likely to prefer your product (see example table). 

Why use conjoint analysis?

When people face challenging trade-offs, we learn what’s truly important to them. Conjoint analysis doesn’t allow people to say that everything is important, which can happen in typical rating scale questions, but rather forces them to choose between competing realistic options. By systematically varying product features and prices in a conjoint survey and recording how people choose, you gain information that far exceeds standard concept testing.

If you want to predict how people will react to new product formulations or prices, you cannot rely solely on existing sales data, social media content, qualitative inquiries, or expert opinion.

What-if market simulators are a key reason decision-makers embrace and continue to request conjoint analysis studies. With the model built from choices in the conjoint analysis, market simulators allow managers to test feature/pricing combinations in a simulated shopping/choice environment to predict how the market would react.

What are the outputs of Conjoint Analysis?

The preference scores that result from a conjoint analysis are called utilities. The higher the utility, the higher the preference.  Although you could report utilities to others, they are not as easy to interpret as the results of market simulations that are market choices summing to 100%. 

Attribute importances are another traditional output from conjoint analysis.  Importances sum to 100% across attributes and reflect the relative impact each attribute has on product choices.  Attribute importances can be misleading in certain cases, however, because the range of levels you choose to include in the experiment have a strong effect on the resulting importance score. 

The key deliverable is the what-if market simulator.  This is a decision tool that lets you test thousands of different product formulations and pricing against competition and see what buyers will likely choose.  Make a change to your product or price and run the simulation again to see the effect on market choices.  You can use our market simulator application or our software can export your market simulator as an Excel sheet. 

How are outputs used? 

Companies use conjoint analysis tools to test improvements to their product, help them set profit-maximizing prices, and to guide their development of multiple product offerings to appeal to different market segments.  Because graphics may be used as attribute levels, CPG firms use conjoint analysis to help design product packaging, colors, and claims.  Economists use conjoint analysis for a variety of consumer decisions involving green energy choice, healthcare, or transportation.  The possibilities are endless.

The Basics of Interpreting Conjoint Utilities

Users of conjoint analysis are sometimes confused about how to interpret utilities. Difficulty most often arises in trying to compare the utility value for one level of an attribute with a utility value for one level of another attribute. It is never correct to compare a single value for one attribute with a single value from another. Instead, one must compare differences in values. The following example illustrates this point:

Brand A 40    Red  20    $ 50   90
Brand B 60    Blue 10    $ 75   40
Brand C 20    Pink  0    $ 100   0

It is not correct to say that Brand C has the same desirability as the color Red. However, it is correct to conclude that the difference in value between brands B and A (60-40 = 20) is the same as the difference in values between Red and Pink (20-0 = 20). This respondent should be indifferent between Brand A in a Red color (40+20=60) and Brand B in a Pink color (60+ 0 = 60).

< see next page >

Sometimes we want to characterize the relative importance of each attribute. We do this by considering how much difference each attribute could make in the total utility of a product. That difference is the range in the attribute’s utility values. We percentage those ranges, obtaining a set of attribute importance values that add to 100, as follows:

For this respondent, the importance of Brand is 26.7%, the importance of Color is 13.3%, and the importance of Price is 60%. Importances depend on the particular attribute levels chosen for the study. For example, with a narrower range of prices, Price would have been less important.

When summarizing attribute importances for groups, it is best to compute importances for respondents individually and then average them, rather than computing importances using average utilities. For example, suppose we were studying two brands, Coke and Pepsi. If half of the respondents preferred each brand, the average utilities for Coke and Pepsi would be tied, and the importance of Brand would appear to be zero!

Source:

Sawtooth Software (2021), What is conjoint analysis [online], accessed 11-10-2021, available at: https://sawtoothsoftware.com/conjoint-analysis