Combining Multiple Testing with Multivariate Singular Spectrum Analysis

TL;DR

This paper evaluates the effectiveness of multivariate Singular Spectrum Analysis (SSA) as a preprocessing step for noisy datasets, demonstrating its ability to enhance signal detection and improve the power of multiple hypothesis tests.

Contribution

It introduces and assesses multivariate SSA as a nonparametric preprocessing technique, comparing it with other methods for denoising and signal extraction in noisy data analysis.

Findings

SSA effectively reduces noise and extracts main signals.

SSA improves the statistical power of subsequent tests.

Multivariate SSA is a promising preprocessing method.

Abstract

Appropriate preprocessing is a fundamental prerequisite for analyzing a noisy dataset. The purpose of this paper is to apply a nonparametric preprocessing method, called Singular Spectrum Analysis (SSA), to a variety of datasets which are subsequently analyzed by means of multiple statistical hypothesis tests. SSA is a nonparametric preprocessing method which has recently been utilized in the context of many life science problems. In the present work, SSA is compared with three other state-of-the-art preprocessing methods in terms of goodness of denoising and in terms of the statistical power of the subsequent multiple test. These other methods are either parametric or nonparametric. Our findings demonstrate that (multivariate) SSA can be taken into account as a promising method to reduce noise, to extract the main signal from noisy data, and to detect statistically significant signal components.