Taylor & Francis Group
Browse
ubes_a_1647844_sm8034.pdf (369.17 kB)

Testing Serial Correlation and ARCH Effect of High-Dimensional Time-Series Data

Download (369.17 kB)
Version 2 2019-08-28, 12:45
Version 1 2019-07-25, 16:30
journal contribution
posted on 2019-08-28, 12:45 authored by Shiqing Ling, Ruey S. Tsay, Yaxing Yang

This article proposes several tests for detecting serial correlation and ARCH effect in high-dimensional data. The dimension of datap=p(n)may go to infinity when the sample sizen. It is shown that the sample autocorrelations and the sample rank autocorrelations (Spearman’s rank correlation) of the L1-norm of data are asymptotically normal. Two portmanteau tests based, respectively, on the norm and its rank are shown to be asymptotically χ2-distributed, and the corresponding weighted portmanteau tests are shown to be asymptotically distributed as a linear combination of independent χ2 random variables. These tests are dimension-free, that is, independent of p, and the norm rank-based portmanteau test and its weighted counterpart can be used for heavy-tailed time series. We further discuss two standardized norm-based tests. Simulation results show that the proposed test statistics have satisfactory sizes and are powerful even for the case of small n and large p. We apply the tests to two real datasets. Supplementary materials for this article are available online.

Funding

Shiqing Ling’s research was supported by Hong Kong Research Grants Commission grants (16307516, 16500117, and 16303118, theme-based projects), NSFC (no. 11731015), and Australian Research Council. Yang’s research was supported by the Fundamental Research Funds for the Central Universities (no. 20720171062) and the NSFC (no. 11801476). R. Tsay’s research is supported in part by Chicago Booth

History