Original fantasy football studies, run on our own database and required to replicate across seasons before we publish them. Every claim here traces back to a sample size and an effect size — including the ones that failed.
One page per player: all 17 games with the opponent, score and margin, roughly 35 stat categories, live ADP across five books, the 2026 offense he plays in with projected share, and what our board says. Free, no account.
Seventeen measured findings, each one a question people actually ask — does rushing yards over expected predict anything, do touchdowns regress, do receivers really eat man coverage, do betting lines beat projections. The prevailing view is stated first so you can check both.
The full inventory: which platforms it connects to, how it scouts your leaguemates from their other leagues and drafts, what it holds on every player, and the rules that stop it inventing a stat. Including what it cannot do.
One long-form study per ranked player, 172 of them. Each charts every week of the season against expected points, splits the year into the phases that actually moved it, and says plainly where to draft him. Start here.
He has outscored his expected points four seasons running — 58 points above it in 2025 alone. The coverage data says why: 0.556 EPA per target against man against 0.323 versus zone, across 448 targets. Every week charted, 58 graded prop lines, and the target-share projection that decides what he is actually worth at 24 overall.
We tested 272 stat fields across four positions. Only 41 replicated. The complete record of what predicts fantasy production and what doesn’t — including the advanced metrics that fail, what consensus betting lines know that box scores don’t, the matchup myths that died in testing, and a shelf of our own discarded ideas.
Replication or it doesn’t ship. An effect has to hold the same direction across every season we test before it informs anything on this site. One good season is a coincidence.
We publish the failures. Every study carries a section for what didn’t work, including our own models losing to simpler baselines. Findings you can’t check against their failures aren’t findings.
Effect sizes, not adjectives. “Target share matters” is a take. “+0.217 across 3,222 player stretches, same sign five straight seasons” is a result.
Research, not picks. We study consensus betting lines because they are the most honest public forecast of player production available. Nothing we publish is betting advice.