TY - JOUR
T1 - Some simple estimators for the two-parameter gamma distribution
AU - Saulo, Helton
AU - Bourguignon, Marcelo
AU - Zhu, Xiaojun
AU - Balakrishnan, N.
N1 - Publisher Copyright:
© 2018, © 2018 Taylor & Francis Group, LLC.
PY - 2019/9/14
Y1 - 2019/9/14
N2 - In this paper, we propose two new simple estimation methods for the two-parameter gamma distribution. The first one is a modified version of the method of moments, whereas the second one makes use of some key properties of the distribution. We then derive the asymptotic distributions of these estimators. Also, bias-reduction methods are suggested to reduce the bias of these estimators. The performance of the estimators are evaluated through a Monte Carlo simulation study. The probability coverages of confidence intervals are also discussed. Finally, two examples are used to illustrate the proposed methods.
AB - In this paper, we propose two new simple estimation methods for the two-parameter gamma distribution. The first one is a modified version of the method of moments, whereas the second one makes use of some key properties of the distribution. We then derive the asymptotic distributions of these estimators. Also, bias-reduction methods are suggested to reduce the bias of these estimators. The performance of the estimators are evaluated through a Monte Carlo simulation study. The probability coverages of confidence intervals are also discussed. Finally, two examples are used to illustrate the proposed methods.
KW - Gamma distribution
KW - Maximum likelihood estimator
KW - Method of moments
KW - Modified moment estimator
UR - http://www.scopus.com/inward/record.url?scp=85046636657&partnerID=8YFLogxK
U2 - 10.1080/03610918.2018.1457693
DO - 10.1080/03610918.2018.1457693
M3 - Article
AN - SCOPUS:85046636657
SN - 0361-0918
VL - 48
SP - 2425
EP - 2437
JO - Communications in Statistics: Simulation and Computation
JF - Communications in Statistics: Simulation and Computation
IS - 8
ER -