Tests for Gaussianity of a Stationary Time Series

One of the primary uses of higher order statistics in signal processing has been for detecting and estimation of non- Gaussian signals in Gaussian noise of unknown covariance. This is motivated by the ability of higher order statistics to suppress additive Gaussian noise. In this paper, several methods to test for non- Gaussianity of a given process are presented. These methods include histogram plot, kurtosis test, and hypothesis testing using cumulants and bispectrum of the available sequence. The hypothesis testing is performed by constructing a statistic to test whether the bispectrum of the given signal is non-zero. A zero bispectrum is not a proof of Gaussianity. Hence, other tests such as the kurtosis test should be employed. Examples are given to demonstrate the performance of the presented methods.

Authors:

• Adnan Al-Smadi

Keywords:

• Non-Gaussian
• bispectrum
• kurtosis
• hypothesistesting
• histogram.

References:

[1] A. Al-Smadi and M. Smadi," Study of the reliability of a binary
symmetric channel under non-Gaussian disturbances," International
Journal of Communication Systems, vol. 16, no. 10, pp. 865-973,
December 2003.
[2] S. Zabin and D. Furbeck, "Efficient identification of non-Gaussian
mixtures," IEEE Trans. Comm., vol. 48, pp. 106-117, January 2000.
[3] J. M Mendel," Tutorial on higher order-statistics (spectra) in signal
processing and system theory: Theoretical results and some
applications," Proceedings of the IEEE, vol. 79, pp. 278-305, March
1991.
[4] C.L. Nikias and M.R. Raghveer, "Bispectrum estimation: A digital
signal processing framework," Proceedings of the IEEE, vol.75, no. 7,
pp. 869-891, July, 1987.
[5] A. Al-Smadi & D. M. Wilkes, "Robust and Accurate ARX and ARMA
Model Order Estimation of Non-Gaussian Processes", IEEE Trans. On
Signal Processing, vol. 50, no. 3, pp. 759 -763, March 2002.
[6] A. Al-Smadi, "Cumulant based approach to FIR system identification",
International Journal of Circuit Theory and Applications, vol. 31, no. 6,
pp. 625-636, November, 2003.
[7] D.R. Brillinger, "An Introduction to Polyspectra," Ann. Math. Statist.,
vol. 36, pp. 1351-1374, 1965.
[8] M.Choudhury, S. Shah, and N. Thornhill, "Diagnosis of poor controlloop
performance using higher order statistics," Automatica, vol. 40, pp.
1719-1728, 2004.
[9] D. Montgomery, Introduction to Statistical Quality Control, John Wiley
& Sons, New York, 2000.
[10] D.C. Montgomery and G. C. Runger, Applied Statistics and probability
for Engineers, John Wiley, New York, 1999.
[11] R. Pond, Fundamentals of Statistical Quality Control, Macmillan
College Publishing, New York, 1994.
[12] J. A. Cadzow, "Blind deconvolution via cumulant extrema," IEEE
Signal Processing Mag., vol. 13, no. 5, pp. 24-42, 1996.
[13] Y.Nishiguchi, N. Toda, and S. Usui, "Parametric estimation of Higherorder
spectra by tensor product expansion with coordinate
transformation," Electronics and Communications in Japan, vol. 87, no.
1, pp. 75-83, 2004.
[14] S.A. Kassam, Signal detection in non-Gaussian noise, Springer-Verlag,
New York, 1988.
[15] J. Caillec and R. Garello, "Comparison of statistical indices using third
order statistics for nonlinearity detection," Signal Processing,
vol. 84, pp. 499- 525, 2004.