# Entropic Approach to Multiscale Clustering Analysis

^{1}

^{2}

^{*}

## Abstract

**:**

## 1. Introduction

## 2. Model Selection with the Kullback–Leibler Divergence

## 3. Extreme Value Statistics

## 4. The Multiscale Autocorrelation Function

**Figure 2.**MAF: average chance probability (solid line), with 68% region around the mean value, estimated from isotropic and anisotropic skies generated as explained in the text. The dashed line indicates the value of the dispersion adopted to generate the corresponding mock map: (

**a**) 5, (

**b**) 10 and (

**c**) 20 degrees; (

**d**) isotropic map. (Adapted from [9], reprinted by permission from IOP Publishing, Figure 4).

**Figure 3.**MAF: test power as a function of the percentage of isotropic contamination in a sky of 100 events and 10 randomly distributed sources. We fix the angular scale of clustering in simulations, namely $\rho ={3}^{\circ}$ (left panel) and $\rho ={10}^{\circ}$ (right panel), and we show the test power corresponding to different values of the test significance, ranging from $\alpha =0.1$ to $\alpha ={10}^{-7}$, at the corresponding angular scales.

**Figure 4.**As in Figure 3, but varying the angular scale of clustering in simulations from $\rho ={3}^{\circ}$ to $\rho ={20}^{\circ}$, and fixing the test significance, namely $\alpha =0.1$ (left panel) and $\alpha ={10}^{-5}$ (right panel).

**Figure 5.**MAF. (

**a**) Distribution of $\tilde{p}\left({\Theta}^{\u2605}\right)$ for $n=40,60,80,100$ and 500 events; (

**b**) Distribution of $max\left\{s\right(\Theta \left)\right\}$ for $n=40,60,80,100$ and 500 events. Solid line correspond to the least-square fit of the Gumbel density with parameters $\mu =1.743\pm 0.002$ and $\sigma =0.470\pm 0.002$ (${\chi}^{2}/\text{ndf}=1.1\times {10}^{-5}$). (Adapted from [9], reprinted by permission from IOP Publishing, Figure 6).

## 5. Application to the Physics of UHECRs

**Figure 6.**Expected clustering signal, as a function of the angular scale, from a sky of protons with $E\ge 100$ EeV (in the field of view of Pierre Auger Observatory) and for values of the Hubble parameter ranging from 50 to 100 km/s/Mpc. Sources of 44% of events are AGN within 200 Mpc in the SWIFT-BAT 58-months catalog, whereas the remaining 56% of events are isotropically distributed. The intrinsic luminosity of AGN is taken into account. The clustering for $N=100$ (left panel) and $N=50$ (right panel) is considered. The signal at each angular scale is obtained by averaging over ${10}^{4}$ Monte Carlo realizations.

**Figure 7.**Chance probability (not penalized for the scan over Θ) for clustering as a function of the angular scale, estimated from the set of 27 UHECR events detected with the Pierre Auger Observatory. Results obtained from multiscale autocorrelation function (MAF) and two-points angular correlation function (ACF) are compared.

## 6. Conclusions

## References

- Greisen, K. End to the cosmic-ray spectrum? Phys. Rev. Lett.
**1966**, 16, 748–750. [Google Scholar] [CrossRef] - Zatsepin, G.; Kuz’Min, V. Upper limit of the spectrum of cosmic rays. JETP Lett.
**1966**, 4, 78–80. [Google Scholar] - Kachelrieß, M.; Semikoz, D. Clustering of ultra-high energy cosmic ray arrival directions on medium scales. Astropart. Phys.
**2006**, 26, 10–15. [Google Scholar] [CrossRef] - Cuoco, A.; Hannestad, S.; Haugbølle, T.; Kachelrieß, M.; Serpico, P. Clustering properties of ultra-high-energy cosmic rays. Astrophys. J.
**2008**, 676, 807–815. [Google Scholar] [CrossRef] - Cuoco, A.; Hannestad, S.; Haugbølle, T.; Kachelrieß, M.; Serpico, P. A global autocorrelation study after the first Auger data. Astrophys. J.
**2009**, 702, 825–832. [Google Scholar] [CrossRef] - The Pierre Auger Collaboration. Correlation of the highest-energy cosmic rays with nearby extragalactic objects. Science
**2007**, 318, 938–943. [Google Scholar] - The Pierre Auger Collaboration. Correlation of the highest-energy cosmic rays with the positions of nearby active galactic nuclei. Astropart. Phys.
**2008**, 29, 188–204. [Google Scholar] - The Pierre Auger Collaboration. Update on the correlation of the highest energy cosmic rays with nearby extragalactic matter. Astropart. Phys.
**2010**, 34, 314–326. [Google Scholar] [Green Version] - De Domenico, M.; Insolia, A.; Lyberis, H.; Scuderi, M. Multiscale autocorrelation function: A new approach to anisotropy studies. J. Cosmol. Astropart. Phys.
**2011**, 03. [Google Scholar] [CrossRef] [PubMed] - Shannon, C. A mathematical theory of communication. Bell Syst. Tech. J.
**1948**, 27, 379–423, 623–656. [Google Scholar] [CrossRef] - De Domenico, M.; for The Pierre Auger Collaboration. Bounds on the Density of Sources of Ultra High Energy Cosmic Rays from Pierre Auger Observatory Data. In Proceedings of the 32nd ICRC, Beijing, China, 11 August 2011.
- De Domenico, M.; Insolia, A. Influence of cosmological models on the GZK horizon of ultrahigh energy protons. arXiv
**2012**. [Google Scholar] [CrossRef] - Akaike, H. Information Theory and an Extension of the Maximum Likelihood Principle. In Proceedings of the 2nd International Symposium on Information Theory, Tsahkadsor, Armenia, U.S.S.R., September 2–8, 1971; pp. 267–281.
- Akaike, H. A new look at the statistical model identification. IEEE Trans. Autom. Control
**1974**, 19, 716–723. [Google Scholar] [CrossRef] - Anderson, D.; Burnham, K.; Thompson, W. Null hypothesis testing: Problems, prevalence, and an alternative. J. Wildl. Manag.
**2000**, 64, 912–923. [Google Scholar] [CrossRef] - Plastino, A.; Plastino, A.; Miller, H. On the relationship between the Fisher-Frieden-Soffer arrow of time, and the behaviour of the Boltzmann and Kullback entropies. Phys. Lett. A
**1997**, 235, 129–134. [Google Scholar] [CrossRef] - Plastino, A.; Miller, H.; Plastino, A. Minimum Kullback entropy approach to the Fokker-Planck equation. Phys. Rev. E
**1997**, 56, 3927–3934. [Google Scholar] [CrossRef] - Portesi, M.; Pennini, F.; Plastino, A. Geometrical aspects of a generalized statistical mechanics. Physica A
**2007**, 373, 273–282. [Google Scholar] [CrossRef] - Fuchs, C. Distinguishability and accessible information in quantum theory. arXiv
**1995**. [Google Scholar] - Reginatto, M. Derivation of the equations of nonrelativistic quantum mechanics using the principle of minimum Fisher information. Phys. Rev. A
**1998**, 58, 1775–1778. [Google Scholar] [CrossRef] - Abe, S.; Rajagopal, A. Quantum entanglement inferred by the principle of maximum nonadditive entropy. Phys. Rev. A
**1999**, 60, 3461–3466. [Google Scholar] [CrossRef] - Abe, S. Nonadditive generalization of the quantum Kullback-Leibler divergence for measuring the degree of purification. Phys. Rev. A
**2003**, 68, 32302. [Google Scholar] [CrossRef] - Gersch, W.; Martinelli, F.; Yonemoto, J.; Low, M.; Mc Ewan, J. Automatic classification of electroencephalograms: Kullback-Leibler nearest neighbor rules. Science
**1979**, 205, 193–195. [Google Scholar] [CrossRef] [PubMed] - Burnham, K.; Anderson, D. Kullback-Leibler information as a basis for strong inference in ecological studies. Wildl. Res.
**2001**, 28, 111–120. [Google Scholar] [CrossRef] - Hu, D.; Ronhovde, P.; Nussinov, Z. Replica inference approach to unsupervised multiscale image segmentation. Phys. Rev. E
**2012**, 85, 016101. [Google Scholar] [CrossRef] - Kullback, S.; Leibler, R. On information and sufficiency. Ann. Math. Stat.
**1951**, 22, 79–86. [Google Scholar] [CrossRef] - Kullback, S. The Kullback-Leibler distance. Am. Stat.
**1987**, 41, 340–341. [Google Scholar] - Cover, T.; Thomas, J. Elements of Information Theory; Wiley Series in Telecommunications: Weinheim, Germany, 1991. [Google Scholar]
- Eguchi, S.; Copas, J. Interpreting kullback-leibler divergence with the neyman-pearson lemma. J. Multivar. Anal.
**2006**, 97, 2034–2040. [Google Scholar] [CrossRef] - Sayyareh, A. A new upper bound for Kullback-Leibler divergence. Appl. Math. Sci.
**2011**, 5, 3303–3317. [Google Scholar] - de Haan, L.; Ferreira, A. Extreme Value Theory: An Introduction; Springer Verlag: Berlin, Heidelberg, Germany, 2006. [Google Scholar]
- Gumbel, E. Statistical Theory of Extreme Values and Some Practical Applications: A Series of Lectures; National Bureau of Standards: Washington, DC, USA, 1954. [Google Scholar]
- Gumbel, E. Statistics of Extremes; Dover Pub.: New York, USA, 2004. [Google Scholar]
- Stokes, B.; Jui, C.; Matthews, J. Using fractal dimensionality in the search for source models of ultra-high energy cosmic rays. Astropart. Phys.
**2004**, 21, 95–109. [Google Scholar] [CrossRef] - Baumgartner, W.H.; Tueller, J.; Markwardt, C.; Skinner, G. The Swift-BAT 58 Month Survey; Bulletin of the American Astronomical Society; American Astronomical Society: Washington, DC, USA, 2010; Volume 42, p. 675. [Google Scholar]
- Trivedi, P.; Subramanian, K.; Seshadri, T. Primordial magnetic field limits from cosmic microwave background bispectrum of magnetic passive scalar modes. Phys. Rev. D
**2010**, 82, 123006. [Google Scholar] [CrossRef] - Bonifazi, C.; for The Pierre Auger Collaboration. The angular resolution of the Pierre Auger observatory. Nucl. Phys. B
**2009**, 190, 20–25. [Google Scholar] [CrossRef]

© 2012 by the authors; licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution license (http://creativecommons.org/licenses/by/3.0/.)

## Share and Cite

**MDPI and ACS Style**

De Domenico, M.; Insolia, A.
Entropic Approach to Multiscale Clustering Analysis. *Entropy* **2012**, *14*, 865-879.
https://doi.org/10.3390/e14050865

**AMA Style**

De Domenico M, Insolia A.
Entropic Approach to Multiscale Clustering Analysis. *Entropy*. 2012; 14(5):865-879.
https://doi.org/10.3390/e14050865

**Chicago/Turabian Style**

De Domenico, Manlio, and Antonio Insolia.
2012. "Entropic Approach to Multiscale Clustering Analysis" *Entropy* 14, no. 5: 865-879.
https://doi.org/10.3390/e14050865