TY - JOUR
T1 - On a rapid simulation of the Dirichlet process
AU - Zarepour, Mahmoud
AU - Labadi, Luai Al
N1 - Funding Information:
We thank the anonymous referees and the Associate Editor for their helpful comments, which improved the paper’s presentation. In addition, we extend our gratitude to Professor Raluca Balan and Professor Hemant Ishwaran for their useful suggestions. The research of the authors is supported by the Natural Sciences and Engineering Research Council of Canada (NSERC) .
PY - 2012/5
Y1 - 2012/5
N2 - We describe a simple, yet efficient, procedure for approximating the Lévy measure of a Gamma. (α, 1) random variable. We use this approximation to derive a finite sum-representation that converges almost surely to Ferguson's representation of the Dirichlet process. This approximation is written based on arrivals of a homogeneous Poisson process. We compare the efficiency of our approximation to several other well-known approximations of the Dirichlet process and demonstrate a significant improvement.
AB - We describe a simple, yet efficient, procedure for approximating the Lévy measure of a Gamma. (α, 1) random variable. We use this approximation to derive a finite sum-representation that converges almost surely to Ferguson's representation of the Dirichlet process. This approximation is written based on arrivals of a homogeneous Poisson process. We compare the efficiency of our approximation to several other well-known approximations of the Dirichlet process and demonstrate a significant improvement.
KW - Dirichlet process
KW - Gamma process
KW - Lévy measure
KW - Nonparametric Bayesian
KW - Stick-breaking representation
UR - http://www.scopus.com/inward/record.url?scp=84857275933&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84857275933&partnerID=8YFLogxK
U2 - 10.1016/j.spl.2012.01.020
DO - 10.1016/j.spl.2012.01.020
M3 - Article
AN - SCOPUS:84857275933
SN - 0167-7152
VL - 82
SP - 916
EP - 924
JO - Statistics and Probability Letters
JF - Statistics and Probability Letters
IS - 5
ER -