Comparing Powerwise (PWR) and the NCAA Power Index (NPI): Advising the NCAA Men's Division I Lacrosse Committee

Lawrence Feldman; Matthew Bomparola

arxiv: 2604.12122 · v1 · submitted 2026-04-13 · 📊 stat.AP

Comparing Powerwise (PWR) and the NCAA Power Index (NPI): Advising the NCAA Men's Division I Lacrosse Committee

Lawrence Feldman , Matthew Bomparola This is my paper

Pith reviewed 2026-05-10 15:24 UTC · model grok-4.3

classification 📊 stat.AP

keywords lacrosseranking systemsNCAA Power IndexPowerwisetournament selectionmargin of victorysports analyticsteam ranking

0 comments

The pith

Powerwise outperforms the NCAA Power Index for ranking lacrosse and similar sports with wider victory margins.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper compares Powerwise (PWR) and the NCAA Power Index (NPI) as systems for ranking NCAA teams to decide championship tournament invites. It concludes that NPI may suit hockey but falls short for lacrosse, football, and basketball because those sports feature wider margins of victory that PWR captures more effectively. The evaluation rests on six explicit criteria: accuracy, procedural integrity, objectivity, reproducibility, simplicity, and stability. A reader would care because the chosen ranking method determines which teams receive postseason opportunities.

Core claim

PWR provides superior accuracy, procedural integrity, objectivity, reproducibility, simplicity, and stability compared to NPI when ranking teams in sports that regularly produce wider margins of victory, such as lacrosse.

What carries the argument

The six-criteria evaluation framework of accuracy, procedural integrity, objectivity, reproducibility, simplicity, and stability used to contrast the two ranking systems.

If this is right

Lacrosse selection committees should adopt PWR instead of NPI for determining tournament invites.
NPI can remain in use for hockey where victory margins are narrower.
PWR extends naturally to football and basketball rankings that also feature variable margins.
Switching to PWR would increase the stability and reproducibility of end-of-season selections.
The comparison criteria themselves offer a reusable template for evaluating other ranking methods.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

Similar margin-sensitive comparisons could be run for other team sports to test whether PWR generalizes beyond lacrosse.
If selection committees ignore margin differences, teams with high-scoring wins may be undervalued in NPI-based systems.
Data from future seasons could serve as an ongoing check on whether PWR maintains its edge as game styles evolve.
Adopting PWR might reduce disputes over selection by increasing perceived objectivity and reproducibility.

Load-bearing premise

The six selected criteria are the right standards for judging ranking-system quality and the underlying game data used in the comparison is representative and unbiased.

What would settle it

A direct test on historical lacrosse seasons showing that NPI rankings align more closely with actual postseason results or team performance than PWR rankings.

read the original abstract

This memo compares two methods, Powerwise (PWR) and the NCAA Power Index (NPI), that aim to rank NCAA Division I, II, and III teams on the basis of deservedness of an invite to end-of-season championship tournaments. It find that while the NPI might be a fit for sports like hockey, it falls short of the PWR method for use in ranking team sports that regularly feature somewhat wider margins of victory, including football, basketball, and lacrosse. In comparing the methods, this memo highlights differences in i) accuracy; ii) procedural integrity; iii) objectivity; iv) reproducibility; v) simplicity; and vi) stability; before drawing conclusions.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

This memo claims PWR beats NPI for lacrosse rankings on six qualitative criteria but supplies no data, tests, or validation to support it.

read the letter

The main thing to know is that this is an advisory memo arguing PWR is better than the NCAA Power Index for ranking teams in lacrosse and other sports with wider margins of victory, yet it offers no numbers or checks to back the conclusion. It simply lists six criteria and states its preference. What the memo does reasonably well is lay out the differences in a straightforward list: accuracy, procedural integrity, objectivity, reproducibility, simplicity, and stability. It explains why the authors think NPI works for hockey but falls short elsewhere, which could give the NCAA committee a concrete set of points to discuss. That structured breakdown is the useful part for practitioners who already know the two systems. The soft spots are clear and central. There are no rank correlations with past tournament results, no predictive accuracy numbers, no side-by-side tables on the same games, and no statistical tests. The judgments on which method is more accurate or stable are presented as facts without evidence. It is also unclear whether the six criteria were chosen independently or shaped to favor PWR, which is a common issue in these comparisons. The paper engages only with the two existing methods and does not bring in broader literature or new derivations. This work is aimed at the NCAA lacrosse committee and sports analytics people who handle ranking systems for college athletics. A general statistics reader or someone looking for validated methods will not get much from it. I would not bring this to the next reading group. I would not cite it in my own work. It does not deserve peer review as a research paper because it lacks empirical grounding or a novel contribution that would justify referee time.

Referee Report

2 major / 2 minor

Summary. The manuscript compares Powerwise (PWR) and the NCAA Power Index (NPI) as ranking systems for NCAA Division I lacrosse teams (with extension to other sports), concluding that NPI falls short for sports featuring wider victory margins while PWR is preferable; the comparison rests on a qualitative evaluation across six criteria (accuracy, procedural integrity, objectivity, reproducibility, simplicity, and stability) without quantitative benchmarks.

Significance. If the qualitative distinctions hold and can be grounded in data, the work could inform NCAA committee decisions on tournament selection metrics for lacrosse and similar sports; however, the absence of empirical validation against outcomes (e.g., historical tournament results or predictive accuracy) limits its immediate applicability as a statistical contribution.

major comments (2)

[Abstract and main comparison] Abstract and comparison section: the central claim that 'NPI falls short' of PWR on accuracy and stability for wider-margin sports is asserted without any supporting data, rank correlations, predictive metrics, error bars, or statistical tests on game outcomes; this renders the superiority assessment subjective rather than demonstrated and is load-bearing for the recommendation to the NCAA committee.
[Criteria comparison] Section on the six evaluation criteria: it is unclear whether the criteria were selected independently of the methods or chosen post-hoc in a manner that favors PWR; without explicit justification or pre-specification, the framework risks circularity in declaring one method superior.

minor comments (2)

The manuscript would benefit from a table summarizing the six criteria scores for each method to improve readability and allow direct comparison.
Clarify the data sources and time periods used for any illustrative examples of rankings or margins of victory.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for their constructive comments on our manuscript comparing Powerwise (PWR) and the NCAA Power Index (NPI). We address each major comment below and indicate the revisions we will make to strengthen the paper.

read point-by-point responses

Referee: [Abstract and main comparison] Abstract and comparison section: the central claim that 'NPI falls short' of PWR on accuracy and stability for wider-margin sports is asserted without any supporting data, rank correlations, predictive metrics, error bars, or statistical tests on game outcomes; this renders the superiority assessment subjective rather than demonstrated and is load-bearing for the recommendation to the NCAA committee.

Authors: We agree that the manuscript would be strengthened by incorporating quantitative elements to support the claims. The assessment that NPI falls short for wider-margin sports derives from the explicit treatment of victory margins in the PWR algorithm versus the more threshold-based structure of NPI, which can be shown through direct comparison of their formulas. To address the concern, we will revise the abstract and comparison section to include rank correlations between PWR and NPI from recent lacrosse seasons and illustrative cases of teams with large victory margins. This provides empirical grounding while preserving the qualitative framework. We note that full predictive validation against tournament outcomes would require additional data and analysis beyond the current scope. revision: yes
Referee: [Criteria comparison] Section on the six evaluation criteria: it is unclear whether the criteria were selected independently of the methods or chosen post-hoc in a manner that favors PWR; without explicit justification or pre-specification, the framework risks circularity in declaring one method superior.

Authors: The six criteria are standard desiderata drawn from the literature on evaluating ranking and rating systems in sports analytics and operations research, selected independently of PWR or NPI. We apply them uniformly to both methods. To eliminate any perception of post-hoc selection, we will revise the manuscript by adding a dedicated subsection that pre-specifies the criteria, provides explicit justification for each, and includes citations to prior work on ranking system evaluation. This will demonstrate that the framework is not tailored to favor PWR. revision: yes

Circularity Check

0 steps flagged

No circularity: qualitative comparison uses author-chosen criteria without self-referential reduction

full rationale

The paper presents a side-by-side qualitative comparison of PWR and NPI on six explicitly listed criteria (accuracy, procedural integrity, objectivity, reproducibility, simplicity, stability). No equations, fitted parameters, or derivations appear in the abstract or description. The central claim that NPI falls short for wider-margin sports rests on the authors' assessment of differences rather than any input being renamed or forced as output by construction. No self-citations are invoked as load-bearing premises, and the criteria are stated openly rather than smuggled via prior work. The analysis is self-contained as a memo-style evaluation; any concerns about post-hoc criterion selection or lack of quantitative validation fall under empirical strength, not circularity.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

No mathematical model, free parameters, axioms, or invented entities are described in the abstract; the work is a qualitative and quantitative comparison of two existing ranking procedures.

pith-pipeline@v0.9.0 · 5416 in / 1009 out tokens · 43111 ms · 2026-05-10T15:24:46.668841+00:00 · methodology

discussion (0)

Reference graph

Works this paper leans on

6 extracted references · 6 canonical work pages · 1 internal anchor

[1]

URL https://doi.org/10.2202/1559-0410.1000

doi: 10.2202/1559-0410.1000. URL https://doi.org/10.2202/1559-0410.1000. D. Barrow, I. Drayer, P. Elliott, G. Gaut, and B. Osting. Ranking rankings: An empirical comparison of the predictive power of sports ranking methods.Journal of Quantitative Analysis in Sports, 9(2):187–202,

work page doi:10.2202/1559-0410.1000
[2]

URLhttps://doi.org/10.1515/jqas-2013-0013

doi: 10.1515/jqas-2013-0013. URLhttps://doi.org/10.1515/jqas-2013-0013. T. P. Chartier, E. Kreutzer, A. N. Langville, and K. E. Pedings. Sensitivity and stability of ranking vectors.SIAM Journal on Scientific Computing, 33(3):1077–1102,

work page doi:10.1515/jqas-2013-0013 2013
[3]

SIAM Journal on Scientific Computing , author=

doi: 10.1137/090772745. URL https://doi.org/ 10.1137/090772745. B. J. Coleman, J. M. DuMond, and A. K. Lynch. Evidence of bias in ncaa tournament selection and seeding. Managerial and Decision Economics, 31(7):431–452,

work page doi:10.1137/090772745
[4]

URL https://arxiv.org/abs/cs/0208005. L. Feldman and M. Bomparola. Introducing powerwise (pwr): A pairwise and power rating method for selecting at-large teams to the ncaa division i men’s lacrosse championship. arXiv preprint arXiv:2508.04919, August

work page internal anchor Pith review arXiv
[5]

URLhttps://arxiv.org/abs/2508.04919. K. Massey.Statistical Models Applied to the Rating of Sports Teams. Bluefield College,

work page arXiv
[6]

wins" and earns a

doi: 10.1177/1527002512465413. URL https://doi.org/10.1177/ 1527002512465413. 7 Appendix A: NCAA Power Index (NPI) Explainer The NCAA Power Index (NPI) is a new procedure for selecting teams for NCAA championship tournaments. The old method was extensive and based on the Ratings Percentage Index (RPI). Despite being based on the same two components as the...

work page doi:10.1177/1527002512465413

[1] [1]

URL https://doi.org/10.2202/1559-0410.1000

doi: 10.2202/1559-0410.1000. URL https://doi.org/10.2202/1559-0410.1000. D. Barrow, I. Drayer, P. Elliott, G. Gaut, and B. Osting. Ranking rankings: An empirical comparison of the predictive power of sports ranking methods.Journal of Quantitative Analysis in Sports, 9(2):187–202,

work page doi:10.2202/1559-0410.1000

[2] [2]

URLhttps://doi.org/10.1515/jqas-2013-0013

doi: 10.1515/jqas-2013-0013. URLhttps://doi.org/10.1515/jqas-2013-0013. T. P. Chartier, E. Kreutzer, A. N. Langville, and K. E. Pedings. Sensitivity and stability of ranking vectors.SIAM Journal on Scientific Computing, 33(3):1077–1102,

work page doi:10.1515/jqas-2013-0013 2013

[3] [3]

SIAM Journal on Scientific Computing , author=

doi: 10.1137/090772745. URL https://doi.org/ 10.1137/090772745. B. J. Coleman, J. M. DuMond, and A. K. Lynch. Evidence of bias in ncaa tournament selection and seeding. Managerial and Decision Economics, 31(7):431–452,

work page doi:10.1137/090772745

[4] [4]

URL https://arxiv.org/abs/cs/0208005. L. Feldman and M. Bomparola. Introducing powerwise (pwr): A pairwise and power rating method for selecting at-large teams to the ncaa division i men’s lacrosse championship. arXiv preprint arXiv:2508.04919, August

work page internal anchor Pith review arXiv

[5] [5]

URLhttps://arxiv.org/abs/2508.04919. K. Massey.Statistical Models Applied to the Rating of Sports Teams. Bluefield College,

work page arXiv

[6] [6]

wins" and earns a

doi: 10.1177/1527002512465413. URL https://doi.org/10.1177/ 1527002512465413. 7 Appendix A: NCAA Power Index (NPI) Explainer The NCAA Power Index (NPI) is a new procedure for selecting teams for NCAA championship tournaments. The old method was extensive and based on the Ratings Percentage Index (RPI). Despite being based on the same two components as the...

work page doi:10.1177/1527002512465413