Power in Monte Carlo permutation tests is non-monotonic and can decrease with more sampled permutations, with such decreases occurring infinitely often due to distributional discreteness.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
Proves an impossibility theorem that no feature attribution ranking can be faithful, stable, and complete under collinearity, characterizes the design space as two families, introduces the DASH ensemble method, and formally verifies all claims in Lean 4.
A cycle-counting-ratio estimator for the β-model achieves minimax-optimal MSE and consistency under the weak conditions θ_max→0 and θ_t‖θ‖₁→∞, even at network densities near log n/n.
citing papers explorer
-
More Permutations Do Not Always Increase Power: Non-monotonicity in Monte Carlo Permutation Tests
Power in Monte Carlo permutation tests is non-monotonic and can decrease with more sampled permutations, with such decreases occurring infinitely often due to distributional discreteness.
-
The Attribution Impossibility: No Feature Ranking Is Faithful, Stable, and Complete Under Collinearity
Proves an impossibility theorem that no feature attribution ranking can be faithful, stable, and complete under collinearity, characterizes the design space as two families, introduces the DASH ensemble method, and formally verifies all claims in Lean 4.
-
Subgraph counting estimation for the $\beta$-model in sparse networks
A cycle-counting-ratio estimator for the β-model achieves minimax-optimal MSE and consistency under the weak conditions θ_max→0 and θ_t‖θ‖₁→∞, even at network densities near log n/n.