Abstract
We apply the holonomic gradient method (Nakayama et al. Adv Appl Math 47:639–658, 2011) to the calculation of the probabilities of the multivariate normal distribution. The holonomic gradient method applied to finding the orthant probabilities is found to be a variant of Plackett’s recurrence relation. However, an implementation of the method yields recurrence relations that are more suitable for numerical computation than is Plackett’s recurrence relation. We derive some theoretical results on the holonomic system for the orthant probabilities. These results show that multivariate normal orthant probabilities possess some remarkable properties from the viewpoint of holonomic systems. Finally, we show that the numerical performance of our method is comparable or superior to that of existing methods.
Similar content being viewed by others
References
Aomoto, K.: Analytic structure of Schläfli function. Nagoya Math. J. 68, 1–16 (1977)
Björk, J.E.: Rings of Differential Operators. North-Holland, New York (1979)
Dunnett, C.W., Sobel, M.: Approximations to the probability integral and certain percentage points of a multivariate analogue of Student’s \(t\)-distribution. Biometrika 42, 258–260 (1955)
Gassmann, H.I.: Multivariate normal probabilities: implementing an old idea of Plackett’s. J. Comput. Graph. Stat. 12(3), 731–752 (2003)
Genz, A.: Numerical computation of multivariate normal probabilities. J. Comput. Graph. Stat. 1, 141–150 (1992)
Hashiguchi, H., Numata, Y., Takayama, N., Takemura, A.: Holonomic gradient method for the distribution function of the largest root of a Wishart matrix. J. Multivar. Anal. 117, 296–312 (2013)
Koyama, T.: A holonomic ideal annihilating the Fisher–Bingham integral. Funkc. Ekvacioj 56, 51–61 (2013)
Koyama, T., Nakayama, H., Nishiyama, K., Takayama, N.: Holonomic gradient descent for the Fisher–Bingham distribution on the \(d\)-dimensional sphere. Comput. Stat. 29, 661–683 (2014)
Miwa, A., Hayter, J., Kuriki, S.: The evaluation of general non-centered orthant probabilities. J. R. Stat. Soc. Ser. B 65, 223–234 (2003)
Nakayama, H., Nishiyama, K., Noro, M., Ohara, K., Sei, T., Takayama, N., Takemura, A.: Holonomic gradient descent and its application to the Fisher–Bingham integral. Adv. Appl. Math. 47, 639–658 (2011)
Nishiyama, K., Takayama, N.: Incomplete \({\cal {A}}\)-hypergeometric systems. In: Hibi, T. (ed.) Harmony of Gröbner Bases and the Modern Industrial Society, pp. 193–212. World Scientific, Singapore (2012)
Oaku, T.: Computation of the characteristic variety and the singular locus of a system of differential equations with polynomial coefficients. Jpn. J. Ind. Appl. Math. 11, 485–497 (1994)
Oaku, T.: Algorithms for integrals of holonomic functions over domains defined by polynomial inequalities. J. Symb. Comput. 50, 1–27 (2013)
Oaku, T., Shiraki, Y., Takayama, N.: Algorithms for D-Modules and Numerical Analysis. Computer Mathematics, pp. 23–39. World Scientific, Singapore (2003)
Plackett, R.L.: A reduction formula for normal multivariate integrals. Biometrika 41(3/4), 351–360 (1954)
Saito, M., Sturmfels, B., Takayama, N.: Gröbner Deformations of Hypergeometric Differential Equations. Springer, Berlin (2000)
Schläfli, L.: On the multiple integral \(\int ^n dxdy\dots dz\) whose limits are \(p_1=a_1x+b_1y+\dots +h_1z>0,\quad p_2>0,\dots , p_n>0\) and \(x^2+y^2+\dots +z^2<1\). Q. J. Pure Appl. Math. 2, 269–301; 3, 54–68, 97–108 (1858)
Schwartz, L.: Théorie des Distributions. Hermann, Paris (1966)
Acknowledgments
The first author is a research fellow of Japan Society for the Promotion of Science. His work is supported by Grant-in-Aid for JSPS Fellows 26.3125. The second author is supported by JSPS Grant-in-Aid for Scientific Research No. 25220001.
Author information
Authors and Affiliations
Corresponding author
About this article
Cite this article
Koyama, T., Takemura, A. Calculation of orthant probabilities by the holonomic gradient method. Japan J. Indust. Appl. Math. 32, 187–204 (2015). https://doi.org/10.1007/s13160-015-0166-8
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13160-015-0166-8