时间序列相关性与科莫哥洛夫复杂性:从豪斯多夫维度的角度
Time Series Correlations and Kolmogorov Complexity: A Hausdorff Dimension Perspective
AI总结:
本文从豪斯多夫维度角度探讨时间序列相关性,指出科莫哥洛夫复杂性能有效避免虚假正相关,通过耦合逻辑映射和多变量分数布朗运动模型验证低复杂度序列更易产生虚假正相关。
摘要:
时间序列分析中虚假相关常见,因低复杂度模式可产生高皮尔逊相关性。本文认为科莫哥洛夫复杂性作为抗压缩性,能有效避免此类假阳性。通过有效豪斯多夫维度显示,两个独立序列间偶然相关概率随复杂度指数衰减,而噪声会膨胀观测复杂度,需实际中考虑。通过耦合逻辑映射和多变量分数布朗运动(mfBm)模型验证,低复杂度序列更易产生假阳性。引入联合复杂度指标 $ J_{\rm LZ} = \sqrt{\widetilde{C}_{\rm LZ}(x)\widetilde{C}_{\rm LZ}(y)} $,其捕捉联合高复杂度而非个体复杂度相似性。其阈值可从mfBm假阳性曲线校准。在逻辑映射中,$J_{\rm LZ}$也预示个体复杂度在同步前崩溃。建议首先建立平稳性,然后报告$J_{\rm LZ}$与$ρ$,并对低复杂度序列间的高相关性持怀疑态度。
英文摘要:
Spurious correlations are common in time-series analysis because simple, low-complexity patterns can produce high Pearson correlations even between unrelated series. We argue that Kolmogorov complexity, interpreted as resistance to compression, provides a principled safeguard against such false positives. Using effective Hausdorff dimension, we show that the probability of accidental correlation between two independent series decays exponentially with their complexity, while noise can inflate observed complexity and must therefore be accounted for in practice. We illustrate these ideas with coupled logistic maps and multivariate fractional Brownian motion (mfBm), where the Hurst parameter \(H\) controls both complexity and Hausdorff dimension \((\dim_H = 2 - H)\). Both models show that false positives are much more common among low-complexity series than among high-complexity ones. We introduce the joint complexity indicator \[ J_{\rm LZ} = \sqrt{\widetilde{C}_{\rm LZ}(x)\widetilde{C}_{\rm LZ}(y)}, \] which captures joint high complexity rather than simple similarity between individual complexities. Its threshold can be calibrated from the mfBm false-positive curve. In logistic maps, \(J_{\rm LZ}\) also anticipates the collapse of individual complexity just before synchronization. We recommend establishing stationarity first, then reporting \(J_{\rm LZ}\) alongside \(ρ\), and treating high correlation among low-complexity series with skepticism.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。