Nonsense rank correlations between independent random walks

Yule's nonsense correlation persists for Spearman's rho and Kendall's tau between independent random walks. Neither coefficient concentrates at zero as the sample size grows. For centred random walks with finite increment variances, we derive a universal joint limit expressed through Brownian occupation functionals. Integral formulas give limiting variances of approximately 0.222 and 0.108, respectively, below the Pearson value of 0.241. Rank correlations thus reduce the limiting dispersion on their respective coefficient scales. We prove that both marginal limits have symmetric densities and represent them exactly as limits of polynomial densities determined by Gaussian moment integrals. Spearman's conventional t test and Kendall's normal approximation are asymptotically invalid, with rejection probabilities tending to one under process independence.

Authors

Publication Details

Journal
arXiv (Cornell University)
Published
2026-11-16
DOI
https://doi.org/10.48550/arxiv.2611.20572
Primary Topic
Probability and Statistical Research
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Nonsense rank correlations between independent random walks

Zhu Liping, Zhongming Xie
arXiv (Cornell University)
Probability and Statistical Research
preprint

Nonsense rank correlations between independent random walks

Zhu Liping, Zhongming Xie
preprint en

Abstract

Yule's nonsense correlation persists for Spearman's rho and Kendall's tau between independent random walks. Neither coefficient concentrates at zero as the sample size grows. For centred random walks with finite increment variances, we derive a universal joint limit expressed through Brownian occupation functionals. Integral formulas give limiting variances of approximately 0.222 and 0.108, respectively, below the Pearson value of 0.241. Rank correlations thus reduce the limiting dispersion on their respective coefficient scales. We prove that both marginal limits have symmetric densities and represent them exactly as limits of polynomial densities determined by Gaussian moment integrals. Spearman's conventional t test and Kendall's normal approximation are asymptotically invalid, with rejection probabilities tending to one under process independence.

arXiv (Cornell University)
Probability and Statistical Research
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon