## Electronic Journal of Statistics

### A test of Gaussianity based on the Euler characteristic of excursion sets

#### Abstract

In the present paper, we deal with a stationary isotropic random field $X:{\mathbb{R}}^{d}\to{\mathbb{R}}$ and we assume it is partially observed through some level functionals. We aim at providing a methodology for a test of Gaussianity based on this information. More precisely, the level functionals are given by the Euler characteristic of the excursion sets above a finite number of levels. On the one hand, we study the properties of these level functionals under the hypothesis that the random field $X$ is Gaussian. In particular, we focus on the mapping that associates to any level $u$ the expected Euler characteristic of the excursion set above level $u$. On the other hand, we study the same level functionals under alternative distributions of $X$, such as chi-square, harmonic oscillator and shot noise. In order to validate our methodology, a part of the work consists in numerical experimentations. We generate Monte-Carlo samples of Gaussian and non-Gaussian random fields and compare, from a statistical point of view, their level functionals. Goodness-of-fit $p-$values are displayed for both cases. Simulations are performed in one dimensional case ($d=1$) and in two dimensional case ($d=2$), using R.

#### Article information

Source
Electron. J. Statist. Volume 11, Number 1 (2017), 843-890.

Dates
First available in Project Euclid: 28 March 2017

https://projecteuclid.org/euclid.ejs/1490688316

Digital Object Identifier
doi:10.1214/17-EJS1248

Zentralblatt MATH identifier
1362.62098

Subjects
Primary: 62G10: Hypothesis testing
Secondary: 60G10: Stationary processes 60G15: Gaussian processes 60G60: Random fields

#### Citation

Di Bernardino, Elena; Estrade, Anne; León, José R. A test of Gaussianity based on the Euler characteristic of excursion sets. Electron. J. Statist. 11 (2017), no. 1, 843--890. doi:10.1214/17-EJS1248. https://projecteuclid.org/euclid.ejs/1490688316

#### References

• [1] Adler R. (2008). Some new random field tools for spatial analysis., Stochastic Environmental Research and Risk Assessment, 22, 809–822.
• [2] Adler R. J., Bartz K., Kou S., Monod A. (2014). Estimating thresholding levels for random fields via Euler characteristics., Preprint.
• [3] Adler R. J., Taylor J. E. (2007)., Random Fields and Geometry. Springer Monographs in Mathematics. Springer.
• [4] Arcones M. A. (1994). Limit theorems for nonlinear functionals of a stationary Gaussian sequence of vectors., Annals of Probability, 22, 2242–2274.
• [5] Azaïs J.-M., Wschebor M., Level Sets and Extrema of Random Processes and Fields. Wiley (2009).
• [6] Biermé H., Desolneux A. (2012). A Fourier approach for the level crossings of Shot Noise processes with jumps., Journal of Applied Probability, 49(1), 100–113.
• [7] Biermé H., Desolneux A. (2016). Level total curvature integral: Euler characteristic and 2D random fields., Preprint. https://hal.archives-ouvertes.fr/hal-01370902.
• [8] Cabaña E. M. (1987). Affine processes: a test of isotropy based on level sets., SIAM Journal on Applied Mathematics, 47(4), 886–891.
• [9] Cammarota V., Marinucci D. (2016) A quantitative central limit theorem for the Euler-Poincare characteristic of random spherical eigenfunctions., Preprint. arXiv:1603.09588.
• [10] Cheng D., Xiao Y. (2016). Excursion probability of Gaussian random fields on sphere., Bernoulli, 22(2), 1113–1130.
• [11] Cuesta-Albertos J. A., Gamboa, F. and Nieto-Reyes, A. (2014). A random-projection based procedure to test if a stationary process is Gaussian., Computational Statistics and Data Analysis, 75, 124–141.
• [12] Epps, T. W. (1987). Testing that a stationary time series is Gaussian., Annals of Statistics 15(4), 1683–1698.
• [13] Estrade A., León J. R. (2016). A central limit theorem for the Euler characteristic of a Gaussian excursion set., Annals of Probability, 44(6), 3849–3878.
• [14] Gabriel E., Allard D., Bacro J.-N. (2011). Estimating and testing zones of abrupt change for spatial data., Statistics and Computing, 21, 107–120.
• [15] Geman D. On the variance of the number of zeros of a stationary Gaussian process., The Annals of Mathematical Statistics, 43, 977–982 (1972).
• [16] Hsing T. (1987). On the intensity of crossings by a shot noise process., Advances in Applied Probability, 19, 743–745.
• [17] Kauderer M. (1993). Modes in n-dimensional first-order systems., Journal of Mathematical Physics, 34, p. 4221.
• [18] Lachièze-Rey R. (2016). Two-dimensional Kac-Rice formula. Application to shot noise processes excursions., Preprint. https://arxiv.org/abs/1607.05467.
• [19] Lelievre T., Rousset M. and Stolz G. (2010)., Free Energy Computations. Imperial College Press.
• [20] Lindgren G. (1974). Spectral moment estimation by means of level crossings., Biometrika, 61(3), 401–418.
• [21] Lindner B. and Schimansky-Geier L. (1999) Analytical approach to the stochastic FitzHugh-Nagumo system and coherence resonance., Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics, 60, 7270–7276.
• [22] Lobato, I. N. and Velasco, C. (2004). A simple test of normality for time series., Econometric Theory, 20(4), 671–689.
• [23] Marinucci D., Vadlamani S. (2016). High-frequency asymptotics for Lipschitz-Killing curvatures of excursion sets on the sphere., Annals of Applied Probability, 26(1), 462–506.
• [24] Nott, D. J., Wilson, R. J. (2000). Multi-phase image modelling with excursion sets., Signal Processing, 80, 125–139.
• [25] Nourdin I., Peccati G. and Podolskij M. (2011). Quantitative Breuer-Major theorems., Stochastic Processes and their Applications, 121, 793–812.
• [26] Planck 2015 results XVI (2016). Isotropy and statistics of the CMB., Astronomy and Astrophysics, 594, A16.
• [27] Rice S. O. (1945). Mathematical analysis of random noise., Bell System Technical Journal, 23 and 24.
• [28] Roberts, A. P., Torquato, S. (1999). Chord-distribution functions of three-dimensional random media: approximate first-passage times of Gaussian processes., Physical Review E, 59(5), 4953–4963.
• [29] Sharpe K. (1978). Some properties of the crossings process generated by a stationary $\chi^2$ process., Advances in Applied Probability, 10, 373–391.
• [30] Subba Rao, T. and Gabr, M. M. (1980). A test for linearity of stationary time series., Journal Of Time Series Analysis, 1, 145–158.
• [31] Taheriyoun A. R. (2012). Testing the covariance function of stationary Gaussian random fields., Statistics & Probability Letters, 82, 606–613.
• [32] Taheriyoun A. R., Shafie K., Jafari Jozani M. (2009). A note on the higher moments of the Euler characteristic of the excursion sets of random fields., Statistics & Probability Letters, 79, 1074–1082.
• [33] Withers C. S., Nadarajah S. (2010). Expansions for the multivariate normal., Journal of Multivariate Analysis, 101, 1311–1316.
• [34] Worsley K. J. (1994). Local maxima and the expected Euler characteristic of excursion sets of $\chi^2$, $F$ and $t$ fields., Advances in Applied Probability, 26, 13–42.
• [35] Worsley K. J. (1995). Estimating the number of peaks in a random field using the Hadwiger characteristic of excursion sets, with applications to medical images., Annals of Statistics, 23, 640–669.
• [36] L. Wu (2001). Large and moderate deviations and exponential convergence for stochastic damping Hamiltonian systems., Stochastic Processes and their Applications, 91, 205–238.