Conjoint analysis: plan for at least 300 respondents, then decide if pricing needs it
Conjoint analysis is worth it for pricing when you face a real packaging decision and can reach 300+ qualified buyers. Before that, cheaper methods get you further.
Conjoint analysis is worth running for pricing only when you face a specific packaging decision and can reach a few hundred qualified buyers. Until you can, cheaper methods usually get you further.
The survey shows people several versions of a product, each mixing features and price differently, and asks them to choose. From thousands of choices, a statistical model estimates how much each feature and price level moves the decision. It answers questions like "does adding priority support justify $20 more a month?"
A made-up example: packaging field-service software
Here is a made-up example used throughout. You sell scheduling and invoicing software to commercial cleaning and maintenance companies and are designing two plans. The open questions: does a mobile app for crews matter more than accounting integrations, and how big a price gap between the plans will buyers accept?
Conjoint asks people to choose, never to name a price
Sawtooth Software, which sells conjoint software, describes three steps:
- Break the product into attributes and levels. Example: price ($99, $149, $199, $249 or $299 a month), crew app (none, basic, full), accounting integration (none, one, several) and support (email, chat, phone).
- Show respondents choice tasks. Each task shows a few product profiles, and the respondent picks one. Sawtooth says a study usually has 8 to 20 of these tasks.
- Model the choices. The model gives each level a preference score, called a "part-worth utility." Sawtooth notes that utilities compare within one attribute but not across attributes. Its main deliverable is a market simulator: you set up competing offers and it predicts shares of choice.
Nobody in the survey is asked "what would you pay?" Sawtooth argues that question is hard to answer without context, while choices between realistic offers reveal price sensitivity indirectly. (Ask a stranger what they would pay for software and you mostly learn how they feel about strangers.)
Wikipedia's overview traces the method to mathematical psychology and credits Paul Green at Wharton with developing it for marketing and Jordan Louviere with the choice-based approach. The earliest studies, in the 1970s, had people rank or rate profile cards instead of choosing.
Sample size is where startup conjoint plans break
Sawtooth's sample size rules of thumb give two quick checks:
- Start with 300 respondents, plus at least 200 per subgroup you want to report separately.
- Show every level at least 500 times across the whole sample, with 1,000 as the safer target. With c levels in the largest attribute, t tasks per person and a profiles per task, each person sees each level about t x a / c times.
In the example, price has 5 levels. With 10 tasks of 3 profiles each, one respondent sees each price level about 10 x 3 / 5 = 6 times. Reaching 500 exposures takes 500 / 6 = about 84 respondents; reaching 1,000 takes about 167. Sawtooth notes this second rule comes from older aggregate models and is only a ballpark. Sawtooth says the simpler 300-respondent rule works well in practice, so plan with that.
Now look at your market. If you want separate results for small cleaning firms and large facilities companies, the rule suggests at least 400 qualified people. In a niche B2B market, finding 400 people who actually choose field-service software may be harder than the analysis.
Run conjoint only when all four conditions hold
- You are choosing between specific packages. If you still don't know which features matter, you are not ready.
- The decision is expensive to get wrong. A pricing change for an existing customer base, or a launch where you can't easily test prices live.
- You can reach enough of the right buyers. Consumer products and large B2B categories usually can. A market with a few hundred buyers usually can't.
- Someone can design it. Wikipedia notes that respondents simplify when shown too many attributes and that poorly designed studies can overvalue emotional features. Sawtooth warns that attribute importance depends heavily on the range of levels you include.
The software is often the cheap part. Sawtooth's pricing page lists a free plan for up to 50 respondents per survey that includes choice-based conjoint, with paid plans quoted on request as annual subscriptions. Recruiting respondents and design time cost more.
Four cheaper methods to use first
- Interviews about real purchases. Have buyers walk through their last comparable purchase, then ask what would make them approve a specific offer. You get no demand curve, but you learn which attributes belong in a study at all. How to research willingness to pay covers the method.
- Best-worst ranking of features (MaxDiff). Respondents repeatedly pick the most and least important item from short lists. It ranks features with a simpler design than conjoint, and Sawtooth's free plan includes it.
- Direct price-sensitivity questions. The Van Westendorp "too cheap / too expensive" set is quick to add to a survey. It measures stated reactions to price, not choices between packages, so treat the result as a range to test.
- Live tests with real offers. Quote different prices to comparable prospects, or test two plan pages. Real purchases beat surveys, given enough volume to see a difference.
For most startups the order is interviews to find the attributes that matter, then a small MaxDiff or conjoint pilot under the free cap to check your design. Run a full study only when the decision justifies 300 or more qualified respondents. Quantitative market research covers survey sampling more broadly.
Your next step
Write down the packaging decision, the attributes and levels, and how many qualified buyers you could realistically survey. If that number is well under 300, start with interviews.
To find those buyers, Instant Expert can search for people who match a description you write, such as "operations managers at commercial cleaning companies" or "product managers who priced B2B software plans." You review who it finds, it sends your invitations, and you pay only for calls that get booked. The directory pages for operations professionals in facilities management and product professionals in enterprise SaaS are one place to start.