Incrementality testing

Know what your marketing actually caused.

Hold a channel out in matched markets and measure what changes. Stella designs the test and validates it, so the number survives the budget meeting.

Start freeTalk to a founder

Included in every plan, free and up. No credit card.

Live demo, ask Stella about holdouts
Hi, I'm Stella.

Ask me anything about incrementality: holdout design, picking test and control markets, how much spend you need to detect lift, or a holdout you have already run. Try one:

Trusted by growth teams who left enterprise measurement vendors

PopSockets
Momofuku
TUSHY
Rough Country
Neighbor
Pattern
Pirani
Plunge
WeightCare
Metro Vein Centers
Rylee + Cru
Miracle
PlantsBasically
Why a holdout

Platform ROAS counts conversions that would have happened anyway.

Attribution credits the last click, not the cause. The only way to know what your ads caused is to hold them out in matched markets and measure the difference.

With Stella, you know.

What a channel actually caused.

The revenue that only happened because the ads ran.

Whether they would have bought anyway.

The conversions your platforms are counting twice.

Your incremental ROAS.

Not the platform number. The one that reconciles.

Whether branded search is incremental.

The test most brands avoid running.

What happens if you turn it off.

Before you find out the expensive way.

Whether the result is solid enough to act on.

The range and the significance, not a lone point estimate.

How it works

Most holdouts are won or lost on location selection.

Stella builds a weighted synthetic control from markets that already moved with your test markets, and you can add confounders like another channel, promotions or seasonality. If the markets did not track before the test, no model rescues it afterwards.

The validated result
Pre-period R²0.94
Pre-period MAPE3.8%
Statistical significancep < 0.05

See the full methodology

Test marketControl marketHistorically correlatedads off in controlIncremental lift
Try it on your own data

Already run a holdout? Put it through Stella, free.

Drop a study you ran elsewhere into the free tier and compare. See which control markets we would have picked, and what the validated result looks like.

Start freeor book a call to walk through it
What clients say

Hear it from the brands we run measurement for.

Jerel Blades
TUSHY

Incrementality is included in every plan, free and up.

How to work with Stella

Have us run it, or run it yourself.

Most clients start with the consultancy. The same platform is also self-serve, from $6,000 down to free.

The consultancy · custom pricing

We build your causal optimization loop, and run it for you.

A PhD data scientist runs the whole thing and hands you decisions, plus the proof to defend them.

Talk to a founderDone right, without dedicating the headcount.
A model built and fit to your data
  • A PhD data scientist runs it end to end
  • Holdout & region/cluster design (even dense, multi-location)
  • Every number shown and explained
  • Board / CEO / CFO-ready decks
  • Active strategy + a testing roadmap
  • Dedicated Slack + a named team

The consultancy isn't for everyone. There's a plan for every budget.

Same platform, run by you: $6,000, $3,000, $750, or free.

Free
$0/mo
Run Stella’s real models on your own data.
Best for seeing what honest measurement looks like
  • One media mix model and one holdout analysis every year
  • Upload a spreadsheet, get a real model back. No connectors to set up.
  • The same models we run for enterprise brands, not spreadsheet math
  • Ask questions about your results in plain English
Support: Not included
Start free
Starter
$750/mo
Know where your sales come from, and prove it with real tests.
Best for smaller brands doing $5M to $10M a year
  • Multi-Touch Attribution: see every touchpoint that leads to a sale
  • Ask buyers how they found you, right after they check out
  • Connect up to 5 sources (Shopify, Amazon, Meta, Google, TikTok) and stop pulling reports by hand
  • One holdout test and one media mix model every year, on data you upload
  • Ask questions about your results in plain English
Support: Ticket support
Start free
Most popular
Professional
$3,000/mo
Incrementality running every day, with no test to set up.
Best for teams who want measurement running all the time
  • Everything in Starter
  • Always-On Incrementality: a live view of how incremental every campaign is, updated daily, with no test to run
  • Unlimited holdouts and media mix models, run straight off your connected data, region by region. Up to 7 sources, no more uploads.
  • See where the next dollar should go, and where a channel is already saturated
  • Ask your data questions from Claude, ChatGPT and your other AI tools
Support: Email support
Start free
Scale
$6,000/mo
Push what actually works back into your ad platforms.
Best for brands running many channels who want to act on the results
  • Everything in Professional
  • We send incremental conversions back to Meta, Google, TikTok and more, so their algorithms optimize for real profit instead of last click
  • All of your Stella data delivered into your own warehouse
  • Unlimited data sources
Support: Slack support and a named contact
Start free
FAQ

Incrementality questions, answered.

How does Stella pick test and control locations?

Location selection is where most holdouts are won or lost. Stella analyzes your pre-period history and selects control markets that have moved together with your test markets, so the comparison is valid before the test even starts. It works even for dense, multi-location footprints, using a weighted synthetic control.

How long does a holdout take?

A geo holdout typically runs 20 to 28 days, longer for high ad-stock channels. If you want a usable read sooner, Always-On Incrementality (Professional and up) produces daily directional iROAS while the holdout incubates the rigorous number.

What can I do on the free tier?

Run a real holdout study, no credit card. Free includes one holdout and one media mix model a year, on data you upload. Already ran a holdout elsewhere? Drop it in and see what our location selection would have recommended before you upgrade anything.

What plan includes incrementality testing?

Every plan, free and up. Always-On Incrementality, which keeps the number current between tests, starts at Professional ($3,000/mo).

Know what your marketing actually caused.

Run a real holdout on your own numbers, free. Or have a founder design the first one with you.

Start freeor talk to a founder