PORTFOLIO UPDATED — SEPTEMBER 23, 2026

§3.2 — Research

Point Shaving in NCAA

Retested Wolfers (2006)'s point-shaving test on 95,781 D-I games — the identifying divergence turns out to be mechanical, not corruption, once heteroskedasticity is modeled correctly.

95,781 D-I games, 2003-2025 · 42 spread models averaged into one line · z_absline coefficient drops 70.5% (0.668 → 0.197) once heteroskedasticity is modeled

joint work with a classmate (Kellen) · data from Todd Beck's prediction tracker (thepredictiontracker.com) · not a solo project

ResearchSports

1. why the standard point-shaving test is broken

›a mechanical fact, not a judgment call
A team favored by S points has exactly S−1 possible winning margins (1, 2, …, S−1) that count as "won but didn't cover." That count grows with S regardless of any behavior on the court — Wolfers' divergence is present by construction. We confirmed this isn't just an argument: simulating margins from a zero-manipulation Normal(spread, σ) distribution reproduces the same divergence pattern seen in the real data, visually indistinguishable from the real chart.

2. the real trial log — 70,207 favorite-won games, four models

›Model 1 — standard probit (Wolfers baseline)LL -39438.4

If Wolfers is right, standardized absolute spread (z_absline) should positively predict winning-without-covering.

P(Y=1) = Φ(β0 + β1·z_absline + β2·z_absline²), Y = 1 if favorite won but didn't cover, conditional on winning.

z_absline: 0.668*** (t=87.09) — large and significant, exactly what Wolfers' reading would predict.

›Model 2 — heteroskedastic probitLL -39013.4

Large-spread blowouts (garbage time, pulled starters) should inflate outcome variance, not just shift the mean — conflating the two is exactly the flaw in Model 1.

Same mean equation, but the latent variance is now itself a function of spread: P(Y=1) = Φ((β0+β1·z)/exp(γ0+γ1·z+γ2·z²)).

z_absline in the mean equation drops from 0.668 to 0.197*** (t=9.11) — a 70% reduction. The variance equation confirms why: z_absline predicts outcome dispersion with coefficient 1.009*** (t=23.45).

›Model 3 — skew-probit, constant αLL -39166.7

Even after correcting variance, the outcome distribution might not be symmetric — the heteroskedastic probit still assumes it is.

Azzalini (1985) skew-normal link with a single shape parameter α estimated jointly with the mean equation.

α = −0.728*** (t=−25.99) — statistically significant asymmetry the first two models structurally can't represent.

›Model 4 — skew-probit, α varying by spreadLL -38962.4

The direction and degree of asymmetry might itself change across the spread distribution — close games and blowouts could be skewed differently.

α = γ0 + γ1·z + γ2·z² + γ3·z³, a cubic in standardized spread, estimated jointly with the mean equation.

Best fit of all four models. Every α-equation coefficient significant at p<0.001 — the shape of asymmetry genuinely shifts with spread size, not just its presence.

3. what the correction actually looks like

7.950.17z=0

σ(z) — outcome variance rises with spread

3.0-2.6z=0

α(z) — skewness shifts with spread, not constant

Both curves computed directly from the paper's own real fitted coefficients (Table 2, Models 2 & 4), plotted over the standardized spread range (z_absline) most favorite-won games actually fall in. Neither is flat — variance genuinely grows with spread size, and the skew genuinely changes sign and magnitude across the distribution rather than sitting at one constant value.

headline numbers

mean-equation coefficient, probit → heteroskedastic probit0.668 → 0.197 (−70.5%)
skew-probit improvement over standard probit+476.0 log-likelihood
constant-α skew parameter-0.728 (t=-25.99)

conclusion

Wolfers' identification strategy is fundamentally flawed — the divergence it relies on is mechanical, reproduced exactly by a zero-manipulation simulation. There is genuine, statistically significant asymmetry in outcomes (the skew-probit's real improvement in fit proves that), but the paper is explicit that asymmetry ≠ point shaving: it's equally consistent with garbage-time substitution patterns, coaches resting starters in blowouts, or betting markets pricing more accurately over time. No concrete evidence of manipulation either way.

← back to Research