The MMM jargon every marketing leader should know

This is the marketing-science leg of Brandformance, co-hosted by Pranav Piyush and Sundar Swaminathan. Every two weeks they break down the concepts behind modern marketing measurement — incrementality, marketing mix modeling, brand versus performance — in plain, practical terms, and bust a few myths along the way.

Pranav Piyush is the co-founder and CEO of Paramark, where he’s building modern marketing measurement — incrementality testing and marketing mix modeling — for growth teams. A long-time marketing leader, he hosts Brandformance.

Sundar Swaminathan is a marketing data science and experimentation advisor to consumer-tech scaleups and the creator of the ExperiMENTAL newsletter and podcast. He previously built and led brand data science at Uber — measuring over a billion dollars of brand spend — and earlier worked on the debt desk at the US Treasury.

The gist

• A plain-English tour of the jargon inside a marketing mix model — the terms a CMO or VP of marketing should recognize without needing a stats degree.

• Almost every term is a statistical representation of human behavior — and almost none has a single “right” definition. The honest answer is usually “it depends.”

• Baselines aren’t fixed “organic” demand; they’re the residue of past marketing, and they always trend toward zero.

• Statistical significance and confidence intervals aren’t objective truth — they’re ways to manage risk.

• Models estimate and build confidence; they don’t predict the future. Judge them on out-of-sample performance, not vendor accuracy claims.

Baseline vs. incremental — and why baselines trend to zero

The most fundamental — and most misunderstood — term. Baseline is what would have happened without marketing; incremental is the additional business marketing drove. But that only holds in the short term (think three to six months), because today’s baseline was itself built by years of past marketing. Sundar’s Nike example: cut brand for years and the whole baseline shifts down.

Pranav’s sharper framing: there is no fixed “organic” demand sitting out in the world. Stop everything and the baseline eventually goes to zero — even a box of cereal loses its shelf placement and visibility once it stops selling. A CFO’s “what would we make if we cut marketing to zero?” is fair for a moment, but you’re just borrowing from future growth. Statisticians define baseline as whatever the model couldn’t explain (the residual) — technically true, but it’s standing in for the same idea. Every definition is partly right, partly wrong.

Control variables — what marketing doesn’t control

Control variables are the things that moved your business but weren’t your marketing decisions — the model needs them to isolate marketing’s true effect. Ironically, they’re the things marketing can’t control: seasonality, price changes, product rollouts, even a one-day Cloudflare outage that quietly drops a month 3–4%.

The list is business-specific: FX rates for fintech, crypto sentiment for crypto, weather for ice cream. The discipline is picking the real needle-movers rather than throwing the whole kitchen sink at the model, which just invites misleading correlations.

Carryover and ad stock — marketing’s memory

These sound like pure statistics but are really representations of psychology — how long people remember your brand after you stop advertising. Turn off Nike today and people still name it tomorrow; ad stock/carryover is the model’s attempt to capture that delayed, decaying effect. Higher mental availability generally means a longer carryover, because competitors take longer to absorb the space you vacate. The name is the metaphor: like grocery stock, the inventory in a buyer’s mind draws down gradually rather than vanishing at once — along a curve.

A practical warning from Sundar: people forget to test for ad stock. Run a three-month cut and measure only those three months and you’ve ignored the residual effect of the marketing that came before — and if your conversion cycle is six to eight weeks, you’ve effectively mismeasured the window. Don’t pull a geo test early just because the first weeks still look fine; that’s leftover ad stock, not the final answer.

Saturation, diminishing returns, and marginal ROAS

Saturation says each additional dollar does less than the last — because your earliest buyers are the most problem- and solution-aware, and every later cohort is harder and costlier to convert. Even Meta, twenty years in, still faces it. And the curve’s shape differs by business: AI may be bending it in a way we haven’t seen historically, while retail’s is far steeper.

Marginal ROAS is the return measured at the current point on that curve, not averaged across the whole thing — so a dollar spent where the curve is still steep looks very different from one where it’s flattening. Sundar adds the other half: saturation is really the cost curve, while ROAS is the intersection of the cost curve and a value (LTV) curve, since later cohorts are also worth less. Spend up to where what you get back equals what you put in — and remember that at very high spend, auction competition itself pushes costs up.

Bayesian, significance, and intervals — risk, not truth

On frequentist vs. Bayesian, both hosts cheerfully admit the limits of their stats depth — and argue that for a marketing leader it mostly doesn’t matter. Bayesian starts with a prediction (a “prior”) and updates as data arrives; frequentist leans on assumptions about distributions. Modern MMM and incrementality vendors have largely standardized on Bayesian, partly because it lets you feed incrementality-test results in as priors. Useful to know, but not a reason to stall.

Statistical significance gets mistaken for objectivity because it says “statistical.” But 95% and 99% are essentially arbitrary historical conventions; significance is really how much risk you’re willing to accept. At Uber, moving zero-cost email tests from 95% to 80% two-tailed let them decide faster and test more, and no one cared. And the pedantic-but-real distinction: a “confidence interval” (frequentist) doesn’t actually mean a 95% chance the true value sits in the range — that’s a “credible interval” (Bayesian). The terms matter less than knowing they describe risk, not ground truth.

Multicollinearity and endogeneity — when the model can’t tell channels apart

Break the scary word down: multi-collinear = multiple things moving together. If a team peanut-butters budget — bumping Meta and Google by the same percentage every month — the two channels move in lockstep and the model can’t separate their effects. No variability, no attribution.

Endogeneity is the cause-and-effect loop. Branded search is the poster child: you don’t control the auction, demand does — so demand drives spend, not the other way around. Run a lot of TV and branded search suddenly looks great, because TV created the demand the model then credits to search. Both terms describe the same underlying problem: relationships in the model that are genuinely hard to untangle into “what moves what.”

Counterfactual and synthetic control

A counterfactual is simply the reverse of your decision — what would have happened if you hadn’t (or had) done the thing. It’s the comparison you need to measure impact. In a clean A/B test, an email test, or a geo test, you can observe the counterfactual directly. In many real situations, you can’t.

That’s where synthetic control comes in: you estimate the counterfactual by stitching together a “Frankenstein” comparison from other markets. Testing in New York with no clean twin? Build a synthetic New York from the useful pieces of San Francisco, Philadelphia and others so the combined line tracks New York before the test — then attribute the gap that opens up during it. It’s not causal proof; it’s a made-up but disciplined stand-in for the control you couldn’t run.

Is the model any good?

MAPE, RMSE, in-sample vs. out-of-sample, backtesting, overfitting — all of it is asking one question: can the model predict data it wasn’t given? Models are dangerously good at forcing a pattern onto the data they’ve seen (in-sample); the real test is out-of-sample, predicting a past period that was hidden from it. Do that well and you have more confidence it can handle the genuinely unknown future.

For a CMO, the job isn’t to memorize the metrics — it’s to make sure the data-science team actually did the rigorous validation, especially when there’s pressure to ship. And beware false precision: no model saw the Gulf conflict or the gas-price spike coming, so treat these as estimation and confidence-increasing machines, not prediction machines. Chasing “94% is better than 92%” is exactly the kind of vendor jargon to be skeptical of.

Quote snacks

• “Marketing and baselines in general are always trending towards zero.” — Sundar

• “There’s no organic — everything is made up, everything is artificial.” — Pranav

• “A lot of it does depend. There’s no clear-cut definition for anything — that’s why MMMs are challenging.” — Sundar

• “Statistical significance is how much risk you’re willing to accept in an uncertain decision.” — Sundar

• “Treat the model a bit like a black box, and let someone who can unpack it do more of that thinking for you.” — Sundar

• “Treat these as estimation machines and confidence-increasing machines — not prediction machines.” — Pranav

Why it matters

MMM is becoming a default layer of the modern measurement stack, and the jargon is a big part of why marketing leaders keep it at arm’s length. Demystifying the vocabulary — and showing that most of it reduces to human behavior and risk tolerance — is what lets a CMO ask the right questions instead of deferring entirely or bluffing along.

It also reinforces the series’ core stance: models are tools to be interrogated, not oracles to be obeyed. Know what baseline, ad stock, saturation and significance actually represent, insist your team validates out-of-sample, and you can treat an MMM as a confidence-building instrument rather than a black box you either worship or ignore.

Practical next steps

Stop treating baseline as fixed “organic” demand. Read it as the residue of past marketing, and expect it to decay if you stop investing.

Choose control variables deliberately. Add the real needle-movers for your business — not the whole kitchen sink — so the model doesn’t chase noise.

Respect ad stock in your tests. Add your conversion-cycle window to the end of a test, and don’t pull a geo test early on residual effects.

Set significance by risk, not habit. Match your confidence threshold to the stakes of the decision instead of defaulting to 95%.

Watch for lockstep spend. Vary channel budgets so the model can actually separate them, and flag endogenous channels like branded search.

Insist on out-of-sample validation. Ask your team to prove the model predicts data it wasn’t trained on, and stay skeptical of vendor accuracy claims.