Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: Ryan, Andrew
Format: Recurso digital
Sprache:Englisch
Veröffentlicht: Zenodo 2026
Schlagworte:
Online-Zugang:https://doi.org/10.5281/zenodo.20311243
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Inhaltsangabe:
  • <p>Python simulation code and reproducibility materials for the synthetic null simulations and block-length sensitivity analyses reported in:</p> <p>“Dependence-Aware Lag-Resolved Correlation Analysis in Multi-Sensor Stochastic Systems”.</p> <p>The repository reproduces the Monte Carlo experiments used to evaluate false-positive inflation under exploratory lag scanning with temporal dependence and the calibration behaviour of dependence-preserving block permutation surrogates under varying autocorrelation regimes.</p> <p>The simulations include:</p> <p>- AR(1) null processes with varying autocorrelation strengths<br>- exploratory lag scanning across symmetric lag domains<br>- max-statistic familywise error correction<br>- block-length sensitivity analyses<br>- comparison against naive uncorrected lag scanning</p> <p>All simulations were generated using a fixed master random seed:</p> <p>MASTER_SEED = 42</p> <p>This deposit accompanies the manuscript submitted to Algorithms (MDPI).</p>