Method · high_stress@v1

High stress

Fourth quarter or overtime, a one-score game, and both teams still holding between a 10% and 90% chance to win. The game is live and the snap matters. Wider than the clutch window on purpose: this keeps the whole quarter rather than the last five minutes.

The filter, exactly as it runs

qtr IN (4, 5) AND ABS(score_differential) <= 8 AND vegas_wp BETWEEN 0.1 AND 0.9

Parameters

`max_margin`	8
`wp_low`	0.1
`wp_high`	0.9
`wp_column`	vegas_wp

Where this is arguable

The 10 to 90 band keeps plays that `clutch` would cut, so the two windows are not interchangeable and a number computed under one should never be compared with a number computed under the other.
Win probability leans on the pregame spread, so a team the market underrated spends more of its season inside this window.
One-score is eight points. At three the sample halves and the story sharpens.

These are the objections I already know about. If you have a better one, or you think a different threshold tells a truer story, say so and I will re-run it with your numbers and publish what comes back.

Version 1. Older versions are never deleted, so a piece that citeshigh_stress@v1 stays reproducible after this definition is revised. Source: Data: nflverse (nflfastR), CC-BY 4.0