Conjoint analysis is an advanced, quantitative marketing research method, popular for product and pricing research, that quantifies the value consumers place on the attributes of a product or service.
Conjoint analysis methods use statistical analysis to compute mathematical representations of survey respondents’ preferences for product features, simulate how attribute changes affect demand, and even predict market acceptance of new products before they launch.
This powerful research methodology has become very popular with market researchers and economists for the valuable insight that few other research methods can provide.
Conjoint analysis has become the premier approach for optimizing product features, product pricing, and predicting market success.
A core reason for its popularity and effectiveness is because conjoint survey questions mimic the tradeoffs people make every day in the real world, from relatively simple to very complex choices.
Consider the task of purchasing a new vehicle.
When searching for the “right” vehicle, you typically consider a multitude of variables: type, make (brand), model, year, mileage, price, color, accessories packages, etc. You can see how this is a complex choice to make.
How does anyone possibly make such a complicated decision?
You think about what features matter most to you and then make tradeoffs.
For example, one vehicle could be an acceptable make and model, but at a high price point, whereas a second option is not the ideal make and model but has a more palatable price.
The tradeoff in this simple example is whether the make and model is more preferable to a reasonable price, or vice versa.
Conjoint analysis captures the relationship between different attributes of a product and how preferable they are both comparatively and when combined.
Because of this, conjoint analysis is the gold standard solution for testing multiple features simultaneously, when limited A/B testing doesn’t go far enough.
Let’s take a look at a simplified example of what to expect when running a conjoint analysis experiment and how it works behind the scenes.
To run a conjoint study, you break up the product or service you intend to research into its components, called attributes and levels.
In the example image above, we've broken down the components of a car into attributes of interest for our experiment: brand, engine, type, and price. For each of these attributes we also defined the varying levels that we want to evaluate.
Conjoint analysis software intelligently creates different product combinations using the levels from each attribute.
In simple terms, the conjoint survey design algorithm generates a balanced survey design with product profiles, also known as concepts, formulated to have ideal statistical properties (such as level balance and independence of attributes).
Each profile is made up of multiple conjoined product features (hence, conjoint analysis), such as brand, type, engine, and color, each with systematically varied levels.
These product concepts are then included in a series of questions, usually 8-20, called choice tasks, that make up the conjoint analysis portion of the survey.
At this point, we field the conjoint experiment design and invite respondents to complete the survey.
In the conjoint analysis portion of the survey, respondents choose their most preferred option within sets of product profiles (see the example conjoint analysis question in the image above).
Rather than ask respondents what they subjectively prefer in a product, or which attributes and levels are most important (as when using traditional rating scales and standard survey questions), conjoint analysis employs the more realistic context of asking respondents to choose products from available options.
The final step in the process is where we get to make discoveries and realize insights from the data that we collected.
The conjoint software includes a statistical model that considers the available product options and importantly which alternatives the respondents chose. It statistically deduces which product features are most desired and which attributes have the most impact on customer choice.
Using a logit model coupled with computational algorithms like Hierarchical Bayes (HB), we obtain a full set of preference scores (often called part-worth utilities) for the attribute levels in the study.
The preference scores that result from a conjoint study are called utilities or part-worth utilities.
Utilities quantify respondent preferences. The higher the score, the higher the preference.
Utility scores may be compared between levels within the same attribute but should not be compared across attributes. Because of this there can often be confusion when reporting utilities to others.
For more easily interpretable results consider sharing the results of market simulations (see below) that are market choices summing to 100%.
Attribute importances are another traditional output from conjoint experiments. 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 of a conjoint analysis experiment is the what-if market simulator.
Market simulators are managerial decision support tools wherein you can set up dozens of market scenarios to predict market reactions to different product configurations. Our software includes a powerful market simulator or can even export a working market simulator to an Excel spreadsheet.
With the market simulator, you can test thousands of different product and pricing formulations against the competition and see what buyers will likely choose. Make a change to your product or price and re-run the simulation to see the effect on market choices. Or, set the simulator to do the heavy lifting and automatically search for optimal results.
One of the primary purposes for using conjoint analysis is for gaining strategic insights and making better business decisions relating to product pricing, product feature development, branding and package design, marketing messaging validation, and more.
Conjoint surveys don’t let respondents say that everything is important. It systematically varies product attribute levels to create competing, realistic product profiles and then records what people choose.
Choice-based conjoint eliminates scale use bias present in rating scale questions, and results in insightful data that far exceeds standard concept testing—you learn what’s truly important to customers.
Data resulting from conjoint analysis studies is more realistic and reliable than competing methods. And this is why it has become the gold standard for preference research.
The power and level of insight gained from the conjoint model and its what-if market simulators are why decision-makers in marketing and economics readily embrace and continue to request conjoint analysis studies.
Market simulators allow managers to:
Learn how our industry-leading conjoint analysis software can help you uncover valuable, impactful insights about your audience’s preferences and how market simulators will help you optimize your product offerings.Learn about our conjoint analysis software
Classic questions that marketers are looking for solutions to involve which features to offer in a product or service, how to price that product, and who to target with each of multiple offerings.
Conjoint analysis can help answer all these market research questions. It allows you to test thousands of potential configurations and prices for your product using a single market research survey.
Figuring out how much to charge for a product/service that delivers value to customers while maximizing revenue or profit is the age-old business dilemma.
Directly asking people their willingness to pay in pricing research is problematic due to its difficulty to answer, yielding subjective, unreliable responses.
How much are you willing to pay to double the storage on your next phone or laptop, for example? It's almost an impossible question to answer without a realistic context involving competitive offerings with differing storage and prices.
Given the choices gathered across a sample of respondents, we can tease out the value of a product’s different features and conduct choice simulations to estimate price sensitivity, willingness to pay, and overall demand for different product configurations.
Product managers want to understand their customers’ needs as well as the competitive landscape to help them bring to market the right product at the right price.
A/B tests are limited regarding how many product variations may be tested. With conjoint analysis, thousands of product configurations may be tested using a single survey. We can tease out the importance of features and predict the likely acceptance of just about any possible product configuration and price.
And the end result? An optimal product package ready for successful launch.
Because conjoint analysis presents products in a realistic way, much like buyers would see them in the real world, the researcher can effectively test a multitude of package design and the accompanying claims/branding.
Due to the complex and aesthetic nature of package design, interactions (synergies) between design, colors, and messages can and do occur.
Choice-Based Conjoint (CBC) can detect and model many kinds of interaction effects with precision, making it an excellent solution for optimizing branding, package design and product claims.
At our recent conference, researchers from Procter & Gamble showed how they use our tools for packaging and product claims.
Conjoint analysis is widely used for conducting market simulations, predicting demand, and estimating price sensitivity for various product configurations. But, we can also use conjoint data to group respondents based on their differing preferences. Our software delivers easy-to-use algorithms for grouping respondents that minimize the differences in preference within the groups while maximizing the differences in preference between the groups.
The needs-based segments can be cross-tabulated against other survey data to profile attractive segments and find the greatest opportunities for target market success. Specifically, you can design unique products to appeal to key market segments to enhance your competitiveness in the marketplace.
Health economists use conjoint analysis and other kinds of choice experiments to understand the tradeoffs patients and healthcare providers make in choosing medical treatments, which often feature decisions about the quality and length of life.
This is well illustrated by the Patient Preference Initiative, a framework developed through a public/private partnership between medical technology companies and the Food and Drug Administration (FDA) to collect patient preference data, that recommends conjoint analysis and MaxDiff as good solutions for creating quantitative assessments of the relative desirability or acceptability to patients of different medical treatment approaches.
Many of the innovations we rely on today in our conjoint and choice studies started off in the transportation literature, including the Nobel-prize winning work of Dan McFadden, who invented the statistical model on which modern conjoint analysis and choice experiments rely.
Conjoint analysis helps transportation researchers understand how travelers and urban commuters value and tradeoff various aspects of their travel experience.
To this day the transportation research literature remains one of the best places to find ongoing academic work on choice-based conjoint methods.
Like many traditional marketing projects, environmental impact studies often seek to quantify both the demand and revenue of certain projects with the costs and potential impact of the affected area.
Conjoint analysis can be an extremely helpful tool in these situations to model both sides of a give-and-take relationship between investment and environmental conservation.
The state of North Carolina surveyed a massive 33,000 hunters to get their input on deer hunting season changes to help raise the natural population of bucks.
The direct feedback from constituents trading off realistic scenarios (you can have the longest season with the most tags at the cheapest price) helped guide lawmakers in an extremely practical way.
For over 30 years Sawtooth Software has specialized in conjoint analysis software and we’ve been deemed the experts and authorities for the industry. We’ve even been accused by academics and statisticians that our industry-trusted software makes it too easy! Our customers field more than 17,000 conjoint analysis studies every year.
Indeed, our web-based platform, Discover, makes conjoint analysis as simple as it can get. But, if you need more features and power, we’ve got that too—in spades.
Our desktop-based software, Lighthouse Studio, is a conjoint analysis powerhouse. Its features offer the most power, flexibility, and advanced design and analysis controls in the industry. It allows you to customize your conjoint experiment and analysis more than any other conjoint software on the market.
Conjoint analysis can be complicated and confusing to newcomers, but you don’t have to go it alone.
With decades of experience we’re here to answer your questions and help you on your journey to master the conjoint methods. Through friendly support, trainings, and our vibrant community we all want to help you find the right solution and succeed.
The most widely used conjoint tool for expertly handling a variety of problems in marketing and economics. It asks respondents to choose between a set of realistic product concepts that results in the ability to predict market share for different market scenarios. The go-to approach for brand-package-price CPG studies.
A newer and more advanced conjoint analysis system used when the attribute list grows. It tends to probe more deeply and be a more customized, and engaging experience for the respondent, though it is often two to three times as long as a CBC study.
Advanced analytical tool for multi-check menu choice experiments. Requires a high level of statistical expertise, but opens a world of opportunities for modeling complex consumer choices.
An approach developed in the 1980s that customizes the experience for each respondent. It was designed for situations in which the number of attributes exceeded what could reasonably done with more traditional conjoint methods available at the time. ACA is not used often today.