The InterModel Vigorish (IMV) as a flexible and portable approach for quantifying predictive accuracy with binary outcomes.

Understanding the "fit" of models designed to predict binary outcomes has been a long-standing problem across the social sciences. We propose a flexible, portable, and intuitive metric for quantifying the change in accuracy between two predictive systems in the case of a binary outcome: th...

Full description

Saved in:
Bibliographic Details
Main Authors: Benjamin W Domingue, Charles Rahal, Jessica Faul, Jeremy Freese, Klint Kanopka, Alexandros Rigos, Ben Stenhaug, Ajay Shanker Tripathi
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2025-01-01
Series:PLoS ONE
Online Access:https://doi.org/10.1371/journal.pone.0316491
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850265777037377536
author Benjamin W Domingue
Charles Rahal
Jessica Faul
Jeremy Freese
Klint Kanopka
Alexandros Rigos
Ben Stenhaug
Ajay Shanker Tripathi
author_facet Benjamin W Domingue
Charles Rahal
Jessica Faul
Jeremy Freese
Klint Kanopka
Alexandros Rigos
Ben Stenhaug
Ajay Shanker Tripathi
author_sort Benjamin W Domingue
collection DOAJ
description Understanding the "fit" of models designed to predict binary outcomes has been a long-standing problem across the social sciences. We propose a flexible, portable, and intuitive metric for quantifying the change in accuracy between two predictive systems in the case of a binary outcome: the InterModel Vigorish (IMV). The IMV is based on an analogy to weighted coins, well-characterized physical systems with tractable probabilities. The IMV is always a statement about the change in fit relative to some baseline model-which can be as simple as the prevalence-whereas other metrics are stand-alone measures that need to be further manipulated to yield indices related to differences in fit across models. Moreover, the IMV is consistently interpretable independent of baseline prevalence. We contrast this metric with alternatives in numerous simulations. The IMV is more sensitive to estimation error than many alternatives and also shows distinctive sensitivity to prevalence. We consider its performance using examples spanning the social and natural sciences. The IMV allows for precise answers to questions about changes in model fit in a variety of settings in a manner that will be useful for furthering research and the understanding of social outcomes.
format Article
id doaj-art-722d2ef90eb948eca4ce896380a9143c
institution OA Journals
issn 1932-6203
language English
publishDate 2025-01-01
publisher Public Library of Science (PLoS)
record_format Article
series PLoS ONE
spelling doaj-art-722d2ef90eb948eca4ce896380a9143c2025-08-20T01:54:19ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01203e031649110.1371/journal.pone.0316491The InterModel Vigorish (IMV) as a flexible and portable approach for quantifying predictive accuracy with binary outcomes.Benjamin W DomingueCharles RahalJessica FaulJeremy FreeseKlint KanopkaAlexandros RigosBen StenhaugAjay Shanker TripathiUnderstanding the "fit" of models designed to predict binary outcomes has been a long-standing problem across the social sciences. We propose a flexible, portable, and intuitive metric for quantifying the change in accuracy between two predictive systems in the case of a binary outcome: the InterModel Vigorish (IMV). The IMV is based on an analogy to weighted coins, well-characterized physical systems with tractable probabilities. The IMV is always a statement about the change in fit relative to some baseline model-which can be as simple as the prevalence-whereas other metrics are stand-alone measures that need to be further manipulated to yield indices related to differences in fit across models. Moreover, the IMV is consistently interpretable independent of baseline prevalence. We contrast this metric with alternatives in numerous simulations. The IMV is more sensitive to estimation error than many alternatives and also shows distinctive sensitivity to prevalence. We consider its performance using examples spanning the social and natural sciences. The IMV allows for precise answers to questions about changes in model fit in a variety of settings in a manner that will be useful for furthering research and the understanding of social outcomes.https://doi.org/10.1371/journal.pone.0316491
spellingShingle Benjamin W Domingue
Charles Rahal
Jessica Faul
Jeremy Freese
Klint Kanopka
Alexandros Rigos
Ben Stenhaug
Ajay Shanker Tripathi
The InterModel Vigorish (IMV) as a flexible and portable approach for quantifying predictive accuracy with binary outcomes.
PLoS ONE
title The InterModel Vigorish (IMV) as a flexible and portable approach for quantifying predictive accuracy with binary outcomes.
title_full The InterModel Vigorish (IMV) as a flexible and portable approach for quantifying predictive accuracy with binary outcomes.
title_fullStr The InterModel Vigorish (IMV) as a flexible and portable approach for quantifying predictive accuracy with binary outcomes.
title_full_unstemmed The InterModel Vigorish (IMV) as a flexible and portable approach for quantifying predictive accuracy with binary outcomes.
title_short The InterModel Vigorish (IMV) as a flexible and portable approach for quantifying predictive accuracy with binary outcomes.
title_sort intermodel vigorish imv as a flexible and portable approach for quantifying predictive accuracy with binary outcomes
url https://doi.org/10.1371/journal.pone.0316491
work_keys_str_mv AT benjaminwdomingue theintermodelvigorishimvasaflexibleandportableapproachforquantifyingpredictiveaccuracywithbinaryoutcomes
AT charlesrahal theintermodelvigorishimvasaflexibleandportableapproachforquantifyingpredictiveaccuracywithbinaryoutcomes
AT jessicafaul theintermodelvigorishimvasaflexibleandportableapproachforquantifyingpredictiveaccuracywithbinaryoutcomes
AT jeremyfreese theintermodelvigorishimvasaflexibleandportableapproachforquantifyingpredictiveaccuracywithbinaryoutcomes
AT klintkanopka theintermodelvigorishimvasaflexibleandportableapproachforquantifyingpredictiveaccuracywithbinaryoutcomes
AT alexandrosrigos theintermodelvigorishimvasaflexibleandportableapproachforquantifyingpredictiveaccuracywithbinaryoutcomes
AT benstenhaug theintermodelvigorishimvasaflexibleandportableapproachforquantifyingpredictiveaccuracywithbinaryoutcomes
AT ajayshankertripathi theintermodelvigorishimvasaflexibleandportableapproachforquantifyingpredictiveaccuracywithbinaryoutcomes
AT benjaminwdomingue intermodelvigorishimvasaflexibleandportableapproachforquantifyingpredictiveaccuracywithbinaryoutcomes
AT charlesrahal intermodelvigorishimvasaflexibleandportableapproachforquantifyingpredictiveaccuracywithbinaryoutcomes
AT jessicafaul intermodelvigorishimvasaflexibleandportableapproachforquantifyingpredictiveaccuracywithbinaryoutcomes
AT jeremyfreese intermodelvigorishimvasaflexibleandportableapproachforquantifyingpredictiveaccuracywithbinaryoutcomes
AT klintkanopka intermodelvigorishimvasaflexibleandportableapproachforquantifyingpredictiveaccuracywithbinaryoutcomes
AT alexandrosrigos intermodelvigorishimvasaflexibleandportableapproachforquantifyingpredictiveaccuracywithbinaryoutcomes
AT benstenhaug intermodelvigorishimvasaflexibleandportableapproachforquantifyingpredictiveaccuracywithbinaryoutcomes
AT ajayshankertripathi intermodelvigorishimvasaflexibleandportableapproachforquantifyingpredictiveaccuracywithbinaryoutcomes