Our Choice-based Conjoint uses one of the most robust and sophisticated research methodologies to find the most desired combination of features for your product, service, or package. It takes into account all possible attributes and options within each attribute, calculates the number of unique combinations, and asks respondents to choose one package out of several presented side by side on screen. After several such tasks, the model gets enough information to learn about each attribute and option in comparison to the others.
Once the survey receives enough responses for the model to be satisfied, you will be able to see the importance of each attribute, the strength of each possible package, and the incremental value that each option adds or subtracts from it — allowing you to build and fine-tune your perfect product or service.
💡 Tip: For best results, we recommend a minimum of 750 to 1,500 completes.
Learn more about Conjoint Research Tests in the Lighthouse Academy!
Conjoint Express vs. Segmentation
Use Conjoint Express when you need to minimize costs by asking respondents to respond to the minimum number of screens. Conjoint Express provides real-time analysis and will learn about the preferences of your entire sample group (or a subset if you apply filters), but it won't be able to tell you anything at the individual level of each respondent.
Conjoint Segmentation is a more expensive option, since it will ask respondents to go through approximately twice as many screens to better learn their individual preferences. When a survey finishes fielding, it will take 5–15 minutes to crunch the numbers using Hierarchical Bayesian Modeling — the gold standard of the market research industry. Conjoint Segmentation will arrive at similar results as Conjoint Express, but with much higher confidence. It will also look into clusters of respondents and automatically identify different personas, if such personas emerge from the data.
Setup is identical for both types of conjoint tests, so you can choose either Conjoint Express or Conjoint Segmentation any time, right up until you're ready to launch your survey.
In the Survey Editor
As you add Attributes and Attribute options and change the number of packages per screen, the number of screens presented to respondents (and thus the number of questions used per research test) will update accordingly.
If you would like to look at the design sheet that the platform produces, you can process and download it to analyze on your end. If you have a design sheet created on another platform, you can upload it to your research test here.
Learn more about programming Conjoint Tests here.
Respondent View
When respondents come to the Conjoint question in your survey, they will be asked to complete a series of comparison tasks. The number of tasks per respondent depends on the number of attributes, attribute options, and packages per screen. See how it looks for yourself!
Results Page
Conjoint Express and Conjoint Segmentation come with a live simulator visualization built into the Results page. Express will populate it once there is enough information to build a model — please pay attention to the warnings that alert you if the sample size is too small for drawing conclusions. Conjoint Express will update the findings every time new responses are available on the page.
Since Conjoint Segmentation data analysis takes a few minutes to process, it will be initiated automatically only when the survey is fully completed and out of field. During fielding, once at least 400 responses are collected, you'll have the option to manually initiate the analysis cycle and see interim results; however, we recommend waiting until the full data set is available and analyzed.
By default you will see an average package identified by the model. Click the Best button to roll all columns up to show the best possible combination, or the Worst button to roll all columns down to the worst possible combination. If some options are truncated, you can temporarily hide neighboring columns to read the full name.
The importance level of every attribute identified by the model is visible in the table and expressed through the relative height of the columns in the visualization. The higher a column, the greater impact its options will have on the desirability of the package. Sorting the table by importance will update the visualization.
Additional Conjoint Segmentation Information
In Conjoint Segmentation, sophisticated cluster analysis is automatically conducted on your data. The algorithm connects emerging subsets of the sample with other respondent information (such as traits) as well as their answers to other questions in the survey. This is a live customer persona generation engine, which labels personas with a hypothetical name and a photo to make it easier to distinguish and navigate among them. The engine approximates the most prominent personas in your sample group and shows the package that is perfect for each of them.
Keep in mind that these are not clear-cut filters. When gender, age, and other traits are listed under a persona, it doesn't mean that everyone in the cluster falls within that description — it tells you that these traits were more prevalent in the cluster, statistically speaking, and were best-suited to describe the group. Another explanation or description of the persona may exist outside the dataset, unavailable to the algorithm, so you may want to consider bringing everything you have into the survey. The team is happy to assist if you're surveying existing customers and would like to add transactional background information into the experiment.
The numbered icons across the top of the graph let you toggle among each persona and the cumulative sample. Hide and expand the persona description section to manage your screen space, and you can export the findings for each persona separately.
Toggle between Preference Likelihood (the likelihood that a particular profile would be selected over the theoretical "average profile") and Utility Scores (raw coefficients), which are used to calculate market share, probability impact, package strength, etc. See an example of results here.