MaxDiff is a survey research technique for working out relative preferences. What do people like most? Second-most? Etc. It is useful in situations when simpler techniques – such as asking people to rate things or provide rankings – are considered likely to give poor data. It is also known as maximum difference scaling and best-worst scaling.
Understanding Best-Worst Scaling (MaxDiff)
Whether you call it MaxDiff or best-worst scaling, the goal is the same—to obtain clearer, more reliable preference data. If you ask shoppers to rank attributes like price, quality, convenience, brand reputation, etc, from 1 to 7, they might confidently choose their top and bottom choices, but positions 2 through 6 might be vague or inconsistent.
MaxDiff solves this by forcing respondents to repeatedly choose the best and worst attributes from smaller sets, leading to more meaningful and differentiated insights. It also provides valuable insight into how different attributes compare to one another.
Example of a MaxDiff question
A MaxDiff study involves presenting a sample of respondents with a series of questions, in which each question contains a list of alternatives. Respondents choose which alternative they like the most (best) and which the least (worst). The list of alternatives changes from question to question. I’ve provided an example, below.
Why do people use MaxDiff?
MaxDiff is used to resolve two practical problems with traditional rating scales:
- Poor discrimination between alternatives, with respondents in surveys, often rating multiple alternatives as very important, or 10, on a 10-point scale
- Yeah-saying biases, which are a type of response bias, whereby some respondents typically give much higher ratings than others
Consider the problem of working out what capabilities people would most like in the President of the United States. Asking people to rate the importance of each of the following characteristics would likely not be very useful. We all want a decent and ethical president. But we also want a president who is healthy. And the President needs to be good in a crisis.
We would end up with a whole lot of people rating the capabilities as 10 out of 10 for importance. Some people may give an average rating of 9, whereas others may give an average rating of 5, just because they differ in terms of how strongly they like to state things. MaxDiff is ideal in these kinds of situations.
Overview of the process when doing a MaxDiff study
There are five stages in a MaxDiff study:
- Creating a list of alternatives
- Creating an experimental design
- Collecting the data
- Statistical analysis
- Reporting
You can design and analyse a MaxDiff study in like Displayr — no coding required.
Outputs from a MaxDiff study
The end-point of a MaxDiff study is usually one or both of the following:
- A ranking of alternatives in order of preference. For example, if the study is being used for product-concept testing, the goal is to work out the relative appeal of the concepts.
- An understanding of differences between people in terms of their preferences for the alternatives. For example, a study examining preferences for product attributes may be designed as an input to a segmentation exercise, looking to find segments of people with different preferences.
All of these outputs – utilities, preference shares, and segment comparisons – come standard in MaxDiff software like Displayr, which runs the experimental design and hierarchical Bayes analysis without coding.
MaxDiff vs Conjoint Analysis
The difference between MaxDiff and conjoint analysis: MaxDiff measures the relative importance of individual items — features, claims, benefits — by asking respondents to pick the best and worst from small sets. Conjoint analysis measures how combinations of attributes drive choice, by asking respondents to choose between complete product profiles. Use MaxDiff to prioritize a list; use conjoint analysis to design a product or set a price.
| MaxDiff | Conjoint analysis | |
|---|---|---|
| What it measures | Relative preference for individual items on one list | How multiple attributes trade off against each other in a choice |
| Respondents see | Small sets of items; pick the best and worst | Complete product profiles (features + price); pick the one they’d buy |
| Typical questions answered | Which features, claims, or messages matter most? | What configuration should we build? What will happen to share if we change price? |
| Outputs | Importance scores for each item, comparable on a common scale | Utilities per attribute level; market simulators; price sensitivity |
| Complexity & cost | Simpler to design and field | More design effort; needs careful attribute and level definition |
The two are complements, not competitors: a common workflow is MaxDiff first to shortlist which features matter, then conjoint on the shortlist to find the winning configuration and price.
MaxDiff vs ranking questions
Why use MaxDiff instead of simply asking respondents to rank a list? Three reasons. First, ranking breaks down beyond about seven items — respondents can order their top few and bottom few, but the middle becomes noise, while MaxDiff handles lists of 20 or 30 items comfortably. Second, MaxDiff produces interval-scaled importance scores, so you can say item A is twice as important as item B — a ranking only tells you A came before B. Third, best-worst choices are cognitively easier and more consistent than juggling a full ordering, which shows up as cleaner data. The trade-off: MaxDiff needs more questionnaire space and an analysis step, so for a quick prioritization of five items, a ranking question is fine.
MaxDiff, Concept Testing & New Product Development
One of the reasons MaxDiff is so effective is that it offers a realistic insight into people’s purchasing behavior. By identifying the attributes shoppers value the most and forcing trade-offs, MaxDiff offers a structured way to prioritize specific features when concept-testing new products.
In new product development (NPD), MaxDiff is especially useful when testing product features, packaging designs, messaging, or pricing strategies. It helps researchers determine which elements drive consumer interest and which are less important. Unlike traditional rating scales, MaxDiff eliminates issues like “everything is important” responses, ensuring more reliable insights.
Paired with other concept testing methods, such as monadic testing or conjoint analysis, it helps businesses create offerings that truly resonate with their target audience.
Frequently Asked Questions About MaxDiff
What is MaxDiff?
MaxDiff, short for maximum difference scaling, is a survey method that helps researchers identify which features, products, or messages people value most. It does this by asking respondents to choose the best and worst options from small sets of alternatives.
What is a MaxDiff survey?
A MaxDiff survey presents several lists of options and asks respondents to pick their most and least preferred item in each list. The choices reveal clear preferences and avoid the bias that often occurs in standard rating scales.
Why is MaxDiff also called best-worst scaling?
Both names describe the same technique. In best-worst scaling, respondents repeatedly choose the best and worst options, which provides sharper distinctions between attributes than asking for simple ratings.
When should I use a MaxDiff survey?
Use MaxDiff when you need to prioritize attributes, features, or messages – such as during concept testing, brand research, or product development. It’s most helpful when you have many items to compare but want to know which matter most.
What is the difference between MaxDiff and conjoint analysis?
MaxDiff ranks individual items by importance; conjoint analysis measures how combinations of attributes and price drive choice. Use MaxDiff to prioritize a long list of features or messages, and conjoint to configure a product or test pricing.
Is MaxDiff better than ranking?
For more than about seven items, yes – MaxDiff produces more discriminating, interval-scaled scores and is easier for respondents than ordering a long list. For very short lists, a simple ranking question does the job.
Want to know more about MaxDiff please go to our Beginners Guide to MaxDiff? Head on over to the Displayr blog and check out more important market research topics!
