The standard
The numbers we publish tie back to named, dated sources.
Awareness to incrementality: methods we can defend out loud, and numbers a CFO will sign.
Measurement is where a media plan either earns trust or spends it. Every platform grades its own homework; every dashboard flatters the channel that produced it. Added together, the platform-reported totals routinely claim more conversions than the brand actually had.
Our measurement practice runs the disciplines that check each other: surveyed lift against randomized holdouts, mix models against experiments, attribution against both. Numbers that survive that gauntlet go in the report. Numbers that don’t, don’t.
Named
Direct supply
Named publishers are the default path.
Pre‑bid
Fraud screening
Screening built to catch invalid traffic before budget moves.
Early
First reads
Domain-level visibility soon after launch.
Traceable
Claim to source
The numbers we publish tie back to named, dated sources.
The numbers we publish tie back to named, dated sources.
No single method is the truth. The disciplines check each other — surveys against holdouts, models against experiments — until the number holds.
“A real lift study has a control group.”
Exposed audiences surveyed against matched, unexposed controls to quantify what the campaign moved: awareness, consideration, intent, association. Methodology is the whole game — matched cohorts, independent fielding, instruments locked before exposure, and sample sizes powered for the lift you actually care about.
“You don’t know what your media did until you turn it off.”
Randomized experiments — geo holdouts, audience holdouts, placebo cells — answer the only question that settles budget debates: how many of these conversions would have happened anyway? Design and analysis are locked before launch, read against live spend, and the result is the number a finance team will accept.
“MMM is the measurement that won’t be deprecated.”
Bayesian models read spend, exposure and outcomes at aggregate level — no cookies, no IDs, no platform pixel — and estimate each channel’s causal contribution with carryover and saturation built in. As click-based attribution thins out, this is the read everything else gets checked against.
“Last-click is cheap and wrong.”
Credit distributed across the real journey — the display impression weeks ago, the social click, the branded search — on transparent Shapley-value math instead of a black-box score. Journeys resolve at the household, so the read doesn’t reset every time someone switches screens.
“Viewability is a precondition. Attention is the read.”
Viewability says an ad could have been seen; attention measurement quantifies whether it was — eye-tracking panels, biometric sampling, screen-class-weighted dwell models. It reprices exposure quality across formats and feeds planning the way a metric should: validated against lift studies rather than vendor assertion.
“Watch it think.”
PathWave is the research engine behind every MediaPath plan: sourced, dated category intelligence generated against the vertical you’re pitching, with every stat tied to a primary source. It’s the same standard that powers the State of Digital Media report — and the reason our numbers hold up in the room.
Methods prove it; the dashboard is where you watch it. Pacing, spend and trend in continuous access, every optimization logged with the why. Client-ready by default, aligned to the KPIs you set.
Bring the campaign. We’ll bring the holdouts, the models, and the methodology.