Quantile and Copula Spectrum: A New Approach to Investigate Cyclical Dependence in Economic Time Series
- 12 Downloads
This chapter presents a survey of some recent methods used in economics and finance to account for cyclical dependence and account for their multifaced dynamics: nonlinearities, extreme events, asymmetries, non-stationarity, time-varying moments. To circumvent the caveats of the standard spectral analysis, new tools are now used based on copula spectrum, quantile spectrum and Laplace periodogram in both non-parametric and parametric contexts. The chapter presents a comprehensive overview of both theoretical and empirical issues as well as a computational approach to explain how the methods can be implemented using the R Package.
- Hagemann, A. (2013). Robust spectral analysis. arXiv e-prints. https://arxiv.org/abs/1111.1965.
- Hill, J. B., & McCloskey, A. (2014). Heavy tail robust frequency domain estimation, mimeo.Google Scholar
- Kleiner, B., Martin, R. D., & Thomson, D. J. (1979). Robust estimation of power spectra. Journal of the Royal Statistical Society B, 41(3), 313–351.Google Scholar
- Klüppelberg, C., & Mikosch, T. (1994). Some limit theory for the self-normalized periodogram of stable processes. Scandinavian Journal of Statistics, 21(4), 485–491.Google Scholar
- Lee, J., & Subba Rao, S. S. (2012). The quantile spectral density and comparison-based tests for nonlinear time series. arXiv e-prints. https://arxiv.org/abs/1112.2759.
- Li, T.-H. (2013). Time series with mixed spectra: Theory and methods. Boca Raton: CRC Press.Google Scholar
- Li, T. H. (2019). Quantile-frequency analysis and spectral divergence metrics for diagnostic checks of time series with nonlinear dynamics. arXiv:1908.02545.
- Mikosch, T. (1998). Periodogram estimates from heavy-tailed data. In R. A. Adler, R. Feldman, & M. S. Taqqu (Eds.), A practical guide to heavy tails: Statistical techniques for analyzing heavy tailed distributions (pp. 241–258). Boston: Birkhäuser.Google Scholar