🤖 AI Summary
This paper addresses statistical bias induced by missing data in time series. We propose a novel imputation method that explicitly incorporates salient periodic structures. Our core contribution is the Variable-Bandpass Periodic Block Bootstrap (VBPBB) framework, which—uniquely—enables adaptive identification of dominant periodic components and leverages them to guide imputation. Crucially, VBPBB preserves key statistical properties—including mean and variance—while accurately capturing both structural regularity and dynamic temporal patterns. Extensive experiments across diverse scenarios demonstrate that our method significantly outperforms conventional imputation approaches in distributional fidelity and pattern consistency. Furthermore, empirical validation in high-stakes, data-quality-sensitive domains—such as clinical time-series analysis—confirms its robustness and practical utility. By unifying periodic structure learning with statistically grounded resampling, VBPBB establishes a new paradigm for integrity-preserving modeling of periodic time series.
📝 Abstract
Missing data is a pervasive issue in statistical analyses, affecting the reliability and validity of research across diverse scientific disciplines. Failure to adequately address missing data can lead to biased estimates and consequently flawed conclusions. In this study, we present a novel imputation method that leverages significant annual components identified through the Variable Bandpass Periodic Block Bootstrap (VBPBB) technique to improve the accuracy and integrity of imputed datasets. Our approach enhances the completeness of datasets by systematically incorporating periodic components into the imputation process, thereby preserving key statistical properties, including mean and variance. We conduct a comparative analysis of various imputation techniques, demonstrating that our VBPBB-enhanced approach consistently outperforms traditional methods in maintaining the statistical structure of the original dataset. The results of our study underscore the robustness and reliability of VBPBB-enhanced imputation, highlighting its potential for broader application in real-world datasets, particularly in fields such as healthcare, where data quality is critical. These findings provide a robust framework for improving the accuracy of imputed datasets, offering substantial implications for advancing research methodologies across scientific and analytical contexts. Our method not only impute missing data but also ensures that the imputed values align with underlying temporal patterns, thereby facilitating more accurate and reliable conclusions.