Abstract
The paper considers higher-order cumulant spectral estimates obtained by directly Fourier transforming weighted cumulant estimates. Such estimates computationally are different from those based on the finite Fourier transform. These estimates can be looked at continuously as well as directly on submanifolds. The estimates of cumulants are based on unbiased moment estimates. Asymptotic normality is obtained for these estimates and is based on a strong mixing condition and only a finite number of cumulant summability conditions.
Similar content being viewed by others
References
Brillinger, D. R., and Rosenblatt, M. (1967). Asymptotic theory ofkth order spectra, inSpectral Analysis of Time Series, Harris, B. (Ed.), Wiley, New York, pp. 153–188.
Lii, K. S., and Rosenblatt, M. (1988a). Nonminimum phase non-Gaussian deconvolution.J. Multivariate Anal. 27, 359–374.
Lii, K. S., and Rosenblatt, M. (1988b). Cumulant spectral estimates: Bias and covariance, to appear in Proceedings of 3rd Hungarian Colloquium on Limit Theorems.
Rosenblatt, M. (1984). Asymptotic normality, strong mixing and spectral density estimates.Ann. Prob. 12, 1167–1180.
Royden, H. L. (1968).Real Analysis, MacMillan, New York.
Van Ness, J. (1966). Asymptotic normality of bispectral estimates.Ann. Math. Stat. 37, 1257–1272.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Lii, K.S., Rosenblatt, M. Asymptotic normality of cumulant spectral estimates. J Theor Probab 3, 367–385 (1990). https://doi.org/10.1007/BF01045168
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF01045168