Purchase Intent Simulator
Published model · All-or-Nothing Scenarios · Part 2: Fine-Tuning Simulator →
After seeing X beer, 54.7% of beer-buying consumers said they would buy it. What drove that number — and what could have changed it?
Pin every respondent to one chosen response level per package factor and see how purchase intent shifts.
Curious what's happening inside the model when you apply a scenario? See the companion walkthrough Inside the Model — it traces one respondent's answers through the equation and shows how the headline emerges from all 803 individual predictions.
Think a different specification explains this better? Challenge this model — opens the Model Builder with this model's predictors loaded, on the same outcome and brand, so you can add, drop, or replace them and refit.
How to Use This Tool
Explore what drives purchase intent
How to Use This Tool
Explore what drives purchase intent
1. Pick the outcome (optional)
The concept test asked consumers about purchase intent plus several package perceptions — appeal, brand fit, high-quality, and premium. Purchase intent can be explored three ways: the top-2-box cut, the strictest top-1-box cut, and the full ordered 5-point scale (an ordered-logit model that shows how the whole rating distribution shifts, not just the top box). A separate most-often-purchased brand outcome models which of seven collapsed brand categories a consumer buys most — an exploratory multinomial. You're on the published Purchase Intent model — the primary case study with a hand-picked six-variable specification and a fully calibrated fit. Use the outcome picker at the top to explore the others as exploratory auto-built models — same respondents, same simulator, different predictors chosen by Auto-Build.
2. Filter to a subgroup (optional)
Leave the filter at All respondents to use the published full-sample model, or filter to a subgroup like frequent beer drinkers or high-income households. When you pick a subgroup, the simulator refits the current model's predictors on that subgroup's respondents — the same variables with coefficients re-estimated there — and says so in a gray notice. A Build a custom model button lets you ask Auto-Build for a subgroup-specific specification instead; its variables may differ from the headline set, a blue callout names them, and a notice tells you when the sample was too small for a reliable custom model. For the brand-choice outcome, which has no published refit, the custom model remains the default.
3. Set the scenario
Use the preset buttons for a quick start, or use the dropdowns to set each package factor yourself. The colored bar beneath each label shows that variable's model leverage — the purchase intent swing from its worst to best level, holding the others fixed. You can set one factor or several at once; the model accounts for all variables jointly.
4. Run the scenario
Click Run scenario to send your settings through the active model. The result shows the projected purchase intent and a 95% confidence interval. The How certain is this result? chart shows 10,000 simulated outcomes so you can see how much the baseline and your scenario overlap. On the ordered 5-point purchase-intent model, the result also shows how the full rating distribution shifts across all five levels — not just the top-2-box headline.
5. Explore each factor
Click Explore Each Factor after a run to see a full per-variable sensitivity breakdown. Each card shows the predicted purchase intent at every level of that variable, holding your other settings fixed. Combined best/worst cards show the result of taking every variable's best or worst level at once.
6. Switch to Fine-Tuning
All-or-Nothing pins every respondent to one answer per question — useful for testing extreme scenarios that make the model's assumptions visible. If you'd rather shift distributions incrementally (move 10% of negative reactions toward positive, for example), use the Fine-Tuning Simulator link above the scenario panel. Your subgroup filter and outcome choice carry over.
7. Save, share, and reset
Every run is saved to the Saved Scenarios drawer at the bottom of the page — click Load on any card to restore its settings, or Remove to drop it. Use Share scenario to copy a link with your settings encoded, or Reset to baseline to clear and start over. The baseline shown is the model's estimate for whichever filter is active.
Loading simulator…
Couldn't load the simulator
Want to shift distributions instead of pinning to one value? Fine-Tuning Simulator →
Auto-Build Actionable found no movable predictors for this outcome, so this simulator uses the best Standard model instead — its predictors may not be classified as directly movable.
Set the scenario
The number on each card is the variable's incremental contribution — the gain in Tjur R² it adds once the other variables are included, the same quantity reported elsewhere on this site. Bars and ordering use it too, largest first. Hover a number to see how much of the variable's one-at-a-time separation that represents.
Predicted outcome
How did you change the survey responses?
Each pair of bars compares the actual distribution (green) to the distribution under your scenario (red where you changed it). This is what you changed — not the predicted impact, just the input.
How certain is this result?
Every prediction has wiggle room — these histograms show how much. The green bars are the plausible answers for the baseline; the red bars are the plausible answers for your scenario. Where the colors overlap, the two answers are close enough that the model can't cleanly tell them apart.
Set-everyone-to-X table
Click to show predicted outcomes for every level of every variable
Set-everyone-to-X table
Click to show predicted outcomes for every level of every variable
For each variable's level, the predicted outcome if every respondent had that response, all else unchanged. This is the analytic view of the simulator.
Support and calibration
This panel answers two questions. First, is there enough survey data behind your scenario? It shows how many people actually gave the answers you picked, and warns you if any of those answers was given by too few people to trust. Second, how well does the model match the survey?
Explore each factor
For each variable, see how the predicted outcome would change if you switched just that one selection — holding all your other selections fixed. This shows which individual factor settings produce the largest model-implied changes in the current scenario.