TY - JOUR
T1 - Calculating the normalising constant of the Bingham distribution on the sphere using the holonomic gradient method
AU - Sei, Tomonari
AU - Kume, Alfred
N1 - Funding Information:
The first author is supported by JSPS Institutional Program for Young Researcher Overseas Visits.
Publisher Copyright:
© 2013, Springer Science+Business Media New York.
PY - 2013/3
Y1 - 2013/3
N2 - In this paper we implement the holonomic gradient method to exactly compute the normalising constant of Bingham distributions. This idea is originally applied for general Fisher–Bingham distributions in Nakayama et al. (Adv. Appl. Math. 47:639–658, 2011). In this paper we explicitly apply this algorithm to show the exact calculation of the normalising constant; derive explicitly the Pfaffian system for this parametric case; implement the general approach for the maximum likelihood solution search and finally adjust the method for degenerate cases, namely when the parameter values have multiplicities.
AB - In this paper we implement the holonomic gradient method to exactly compute the normalising constant of Bingham distributions. This idea is originally applied for general Fisher–Bingham distributions in Nakayama et al. (Adv. Appl. Math. 47:639–658, 2011). In this paper we explicitly apply this algorithm to show the exact calculation of the normalising constant; derive explicitly the Pfaffian system for this parametric case; implement the general approach for the maximum likelihood solution search and finally adjust the method for degenerate cases, namely when the parameter values have multiplicities.
KW - Bingham distributions
KW - Directional statistics
KW - Holonomic functions
UR - http://www.scopus.com/inward/record.url?scp=84890896369&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84890896369&partnerID=8YFLogxK
U2 - 10.1007/s11222-013-9434-0
DO - 10.1007/s11222-013-9434-0
M3 - Article
AN - SCOPUS:84890896369
SN - 0960-3174
VL - 25
SP - 321
EP - 332
JO - Statistics and Computing
JF - Statistics and Computing
IS - 2
ER -