Analytics, have some humility: a statistical view of fourth-down decision making
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916591090794496 |
|---|---|
| author | Brill, Ryan S. Yurko, Ronald Wyner, Abraham J. |
| author_facet | Brill, Ryan S. Yurko, Ronald Wyner, Abraham J. |
| contents | The standard mathematical approach to fourth-down decision making in American football is to make the decision that maximizes estimated win probability. Win probability estimates arise from machine learning models fit from historical data. These models attempt to capture a nuanced relationship between a noisy binary outcome variable and game-state variables replete with interactions and non-linearities from a finite dataset of just a few thousand games. Thus, it is imperative to knit uncertainty quantification into the fourth-down decision procedure; we do so using bootstrapping. We find that uncertainty in the estimated optimal fourth-down decision is far greater than that currently expressed by sports analysts in popular sports media. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_03490 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Analytics, have some humility: a statistical view of fourth-down decision making Brill, Ryan S. Yurko, Ronald Wyner, Abraham J. Applications The standard mathematical approach to fourth-down decision making in American football is to make the decision that maximizes estimated win probability. Win probability estimates arise from machine learning models fit from historical data. These models attempt to capture a nuanced relationship between a noisy binary outcome variable and game-state variables replete with interactions and non-linearities from a finite dataset of just a few thousand games. Thus, it is imperative to knit uncertainty quantification into the fourth-down decision procedure; we do so using bootstrapping. We find that uncertainty in the estimated optimal fourth-down decision is far greater than that currently expressed by sports analysts in popular sports media. |
| title | Analytics, have some humility: a statistical view of fourth-down decision making |
| topic | Applications |
| url | https://arxiv.org/abs/2311.03490 |