zbMATH — the first resource for mathematics

Approximate maximum likelihood estimation of the Bingham distribution. (English) Zbl 06917839
Summary: Maximum likelihood estimation of the Bingham distribution is difficult because the density function contains a normalization constant that cannot be computed in closed form. Given the availability of sufficient statistics, Approximate Maximum Likelihood Estimation (AMLE) is an appealing method that allows one to bypass the evaluation of the likelihood function. The impact of the input parameters of the AMLE algorithm is investigated and some methods for choosing their numerical values are suggested. Moreover, AMLE is compared to the standard approach which numerically maximizes the (approximate) likelihood obtained with the normalization constant estimated via the Holonomic Gradient Method (HGM). For the Bingham distribution on the sphere, simulation experiments and real-data applications produce similar outcomes for both methods. On the other hand, AMLE outperforms HGM when the dimension increases.
62 Statistics
hgm; ks; MeanShift; R
Full Text: DOI
[1] Arnold, R.; Jupp, P. E., Statistics of orthogonal axial frames, Biometrika, 100, 571-586, (2013) · Zbl 1284.62304
[2] Beaumont, M. A., Approximate Bayesian computation in evolution and ecology, Annu. Rev. Ecol. Evol. Syst., 41, 379-406, (2010)
[3] Bee, M.; Espa, G.; Giuliani, D., Approximate maximum likelihood estimation of the autologistic model, Comput. Statist. Data Anal., 84, 14-26, (2015)
[4] Bee, M.; Trapin, L., A simple approach to the estimation of tukey’s gh distribution, J. Stat. Comput. Simul., 86, 3287-3302, (2016)
[5] Bingham, C., Distributions on the sphere and on the projective plane, (1964), Yale University, (Ph.D. thesis)
[6] Bingham, C., An antipodally symmetric distribution on the sphere, Ann. Statist., 2, 1201-1225, (1974) · Zbl 0297.62010
[7] Boomsma, W.; Mardia, K. V.; Taylor, C. C.; Ferkinghoff-Borg, J.; Krogh, A.; Hamelryck, T., A generative, probabilistic model of local protein structure, Proc. Natl. Acad. Sci., 105, 8932-8937, (2008)
[8] Ciollaro, M., Wang, D., MeanShift, 2016. URL: http://CRAN.R-project.org/package=MeanShift; R package version 1.1-1.
[9] Cressie, N. A.C., Statistics for spatial data, (1991), Wiley
[10] Duong, T., Kde: Kernel smoothing, 2014. URL: http://CRAN.R-project.org/package=kde; R package version 1.9.2.
[11] Fallaize, C. J.; Kypraios, T., Exact Bayesian inference for the Bingham distribution, Stat. Comput., 26, 349-360, (2016) · Zbl 1342.62031
[12] Friel, N.; Pettitt, A. N., Likelihood estimation and inference for the autologistic model, J. Comput. Graph. Statist., 13, 232-246, (2004)
[13] Glasserman, P., Monte Carlo methods in financial engineering, (2003), Springer
[14] Hamelryck, T.; Kent, J.; Krogh, A., Sampling realistic protein conformations using local structural bias, PLoS Comput. Biol., e131, (2006)
[15] Kent, J.T., Ganeiber, A.M., Mardia, K.V., 2013. A new method to simulate the Bingham and related distributions in directional data analysis with applications. http://arxivorg/abs/13108110.
[16] Kent, J. T.; Hamelryck, T., Using the Fisher-Bingham distribution in stochastic models for protein structure, (Barber, S.; Baxter, P. D.; Mardia, K. V.; Walls, R. E., Quantitative Biology, Shape Analysis, and Wavelets, (2005), Leeds University Press), 57-60
[17] Krieger Lassen, N. C.; Juul Jensen, D.; Conradsen, K., On the statistical analysis of orientation data, Acta Crystallogr., A50, 741-748, (1994)
[18] Kume, A.; Walker, S. G., Sampling from compositional and directional distributions, Statistics, 16, 261-265, (2006)
[19] Kume, A.; Walker, S. G., On the Bingham distribution with large dimension, J. Multivariate Anal., 124, 345-352, (2014) · Zbl 1283.60020
[20] Kume, A.; Wood, A. T.A., Saddlepoint approximations for the Bingham and Fisher-Bingham normalising constants, Biometrika, 92, 465-476, (2005) · Zbl 1094.62063
[21] Love, J., Bingham statistics, (Gubbins, D.; Bervera, E., Encyclopedia of Geomagnetism and Paleomagnetism, (2007), Springer), 45-47
[22] Mardia, K. V.; Jupp, P. E., Directional statistics, (2000), Wiley · Zbl 0935.62065
[23] Mardia, K. V.; Zemroch, P. J., Table of maximum likelihood estimates for the Bingham distribution, J. Stat. Comput. Simul., 6, 29-34, (1977) · Zbl 0373.62071
[24] Møeller, J.; Pettitt, A. N.; Reeves, R.; Berthelsen, K. K., An efficient Markov chain Monte Carlo method for distributions with intractable normalising constants, Biometrika, 93, 2, 451-458, (2006) · Zbl 1158.62020
[25] Murray, I., Ghahramani, Z., MacKay, D., 2006. MCMC for doubly-intractable distributions. In: Proceedings of the 22nd Annual Conference on Uncertainty in Artificial Intelligence UAI06, pp. 359-366.
[26] Peel, D.; Whiten, W. J.; McLachlan, G. J., Fitting mixtures of kent distributions to aid in joint set identification, J. Amer. Statist. Assoc., 96, 56-63, (2001)
[27] Pritchard, J. K.; Seielstad, M. T.; Perez-Lezaun, A.; Feldman, M. T., Population growth of human Y chromosomes: A study of Y chromosome microsatellites, Mol. Biol. Evol., 16, 1791-1798, (1999)
[28] Rubio, F. J.; Johansen, A. M., A simple approach to maximum intractable likelihood estimation, Electron. J. Stat., 7, 1632-1654, (2013) · Zbl 1327.62075
[29] Sei, T.; Kume, A., Calculating the normalising constant of the Bingham distribution on the sphere using the holonomic gradient method, Stat. Comput., 25, 321-332, (2015) · Zbl 1331.62105
[30] Sousa, V. C.; Fritz, M.; Beaumont, M. A.; Chikhi, L., Approximate Bayesian computation without summary statistics: the case of admixture, Genetics, 181, 1507-1519, (2009)
[31] Takayama, N., Koyama, T., Sei, T., Nakayama, H., Nishiyama, K., 2015. Hgm: Holonomic Gradient Method and Gradient Descent, R package version 1.11.
[32] Tyler, D. E., Statistical analysis for the angular central Gaussian distribution on the sphere, Biometrika, 74, 579-589, (1987) · Zbl 0628.62054
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.