Detection and inference of changes in high-dimensional linear regression with non-sparse structures

Haeran Cho, Tobias Kley, Housen Li

Research output: Working paperPreprint

3 Downloads (Pure)

Abstract

For data segmentation in high-dimensional linear regression settings, the regression parameters are often assumed to be sparse segment-wise, which enables many existing methods to estimate the parameters locally via $\ell_1$-regularised maximum likelihood-type estimation and then contrast them for change point detection. Contrary to this common practice, we show that the sparsity of neither regression parameters nor their differences, a.k.a. differential parameters, is necessary for consistency in multiple change point detection. In fact, both statistically and computationally, better efficiency is attained by a simple strategy that scans for large discrepancies in local covariance between the regressors and the response. We go a step further and propose a suite of tools for directly inferring about the differential parameters post-segmentation, which are applicable even when the regression parameters themselves are non-sparse. Theoretical investigations are conducted under general conditions permitting non-Gaussianity, temporal dependence and ultra-high dimensionality. Numerical results from simulated and macroeconomic datasets demonstrate the competitiveness and efficacy of the proposed methods.
Original languageEnglish
DOIs
Publication statusPublished - 4 Mar 2024

Bibliographical note

Implementation is available at https://github.com/tobiaskley/inferchange. In version 2, an application to FRED-MD data is added

Keywords

  • stat.ME
  • math.ST
  • stat.TH

Fingerprint

Dive into the research topics of 'Detection and inference of changes in high-dimensional linear regression with non-sparse structures'. Together they form a unique fingerprint.

Cite this