CPG Concept-Test Case Study
In a 2025 craft-beer concept test, 54.7% of beer-buying consumers said they would purchase X beer. What drove that intent — and how would the answer change for a different income bracket, a different region, or a different level of brand awareness? Five tools let you explore.
Six Ways to Engage with the Data
Two simulators run the published 6-variable purchase-intent account; a stress test pressure-tests the 54.7% headline; a guided walkthrough opens the model up; an explorer and a model builder let anyone investigate any of five outcomes and build their own competing models.
All-or-Nothing Simulator
Pin every respondent to one chosen response level per package factor and see how the 54.7% top-2 purchase intent shifts. Runs on the published model — or a subgroup-specific refit when you filter to a subgroup.
Try itFine-Tuning Simulator
Same published model — or a subgroup refit — but redistribute response shares gradually rather than pinning. Watch how small distributional changes move the purchase-intent needle.
Try itNon-Response Test
Specify a nonresponse pattern and see whether the 54.7% top-2 purchase intent would survive it. A vulnerability check on the released score, separate from the explanatory model.
Try itInside the Model
A guided walkthrough of how the published 6-variable model turns one consumer's package-reaction answers into a predicted top-2 purchase-intent probability — and how those individual probabilities collapse into the 54.7% headline.
Try itSurvey Explorer
Browse the raw responses. See how consumers reacted to each package factor, which questions moved together, and how one group compared to another. Frequencies, cross-tabs, and correlations — against any of the five outcomes.
Try itModel Builder
Pick any of five outcomes — purchase intent, package appeal, brand fit, high-quality, premium — and refit with whichever predictors you choose. Add or remove items, refit on a subgroup, or let Auto-Build find the best combination. See where the published purchase-intent account holds up — or model an outcome it doesn't cover.
Try itAbout Concept Testing
How a concept test works
1. Show the concept
Respondents see a package design, ad mockup, or product description.
2. Capture reactions
A battery of questions probes appeal, fit, relevance, and intent — typically on 5-point scales.
3. Model what matters — and keep modeling
Statistical modeling identifies which reactions actually predict purchase intent. Most concept tests stop here; this one lets you keep going — refit on subgroups, swap predictors, stress the headline against nonresponse.
Package design
The visual concept shown to respondents
Purchase intent
5-point scale, top-2 box modeled
Attribute reactions
Twenty package-perception predictors
Subgroup cuts
Eight subgroup variables for refits
The Concept-Test Survey
Beer-category respondents were shown a new package concept and asked a battery of reaction questions. Purchase intent was captured on a 5-point scale; the top-2 box (Extremely / Very likely) is the modeled outcome.
The published logistic model is validated against Stata 18 to four decimal places.
What the survey measured:
Want this kind of analytical layer on your concept-test data?
emi Research Solutions delivers Mirror engagements like this to CPG brand and insights teams — from concept tests to brand trackers — powered by the Electric Insights analytical engine.