A Frequency Domain Test for Propriety of Complex-Valued Vector Time Series

TL;DR

This paper introduces a frequency domain test for assessing whether complex-valued vector time series are proper, effectively identifying frequency bands of non-propriety with high accuracy, especially for small sample sizes.

Contribution

It develops a practical hypothesis testing methodology for propriety in complex-valued vector time series, addressing limitations of existing asymptotic approaches and providing accurate results for small spectral tapers.

Findings

The proposed test accurately controls rejection rates.

It outperforms existing methods in small-sample scenarios.

Application to ocean data demonstrates practical utility.

Abstract

This paper proposes a frequency domain approach to test the hypothesis that a complex-valued vector time series is proper, i.e., for testing whether the vector time series is uncorrelated with its complex conjugate. If the hypothesis is rejected, frequency bands causing the rejection will be identified and might usefully be related to known properties of the physical processes. The test needs the associated spectral matrix which can be estimated by multitaper methods using, say, $K$ tapers. Standard asymptotic distributions for the test statistic are of no use since they would require $K \rightarrow \infty,$ but, as $K$ increases so does resolution bandwidth which causes spectral blurring. In many analyses $K$ is necessarily kept small, and hence our efforts are directed at practical and accurate methodology for hypothesis testing for small $K.$ Our generalized likelihood ratio statistic combined with exact cumulant matching gives very accurate rejection percentages and outperforms other methods. We also prove that the statistic on which the test is based is comprised of canonical coherencies arising from our complex-valued vector time series.Our methodology is demonstrated on ocean current data collected at different depths in the Labrador Sea. Overall this work extends results on propriety testing for complex-valued vectors to the complex-valued vector time series setting.