您的位置：山东大学 -> 科技期刊社 -> 《山东大学学报（理学版）》

《山东大学学报(理学版)》 ›› 2023, Vol. 58 ›› Issue (10): 24-31.doi: 10.6040/j.issn.1671-9352.0.2023.151

•   • 上一篇    下一篇

带Lévy噪声的Lotka-Volterra竞争模型的参数估计

张诗苗(),吕艳*()   

  1. 南京理工大学数学与统计学院, 江苏 南京 210094
  • 收稿日期:2023-04-10 出版日期:2023-10-20 发布日期:2023-10-17
  • 通讯作者: 吕艳 E-mail:2813091458@qq.com;lvyan1998@aliyun.com
  • 作者简介:张诗苗(1999—), 女, 硕士研究生, 研究方向为随机微分方程的参数估计. E-mail: 2813091458@qq.com
  • 基金资助:
    国家自然科学基金资助项目(12371243)

Parameter estimation for competitive Lotka-Volterra model with Lévy noise

Shimiao ZHANG(),Yan LYU*()   

  1. School of Mathematics and Statistics, Nanjing University of Science and Technology, Nanjing 210094, Jiangsu, China
  • Received:2023-04-10 Online:2023-10-20 Published:2023-10-17
  • Contact: Yan LYU E-mail:2813091458@qq.com;lvyan1998@aliyun.com

RichHTML

0

PDF (PC)

111

摘要：

基于最小二乘原理, 考虑离散观测下Lévy噪声驱动的随机二种群Lotka-Volterra竞争系统的参数估计问题。讨论在噪声强度ε→0和样本量n→∞的情况下, 参数估计量的渐近一致性, 并得到了估计量的渐近分布。最后, 给出竞争模型参数估计的数值模拟, 结果与理论一致。

关键词: Lotka-Volterra模型, Lévy噪声, 最小二乘估计, 渐近一致性

Abstract:

Based on the principle of least square and the technique of discretization, parameter estimation problem for stochastic two-species Lotka-Volterra competitive system driven by Lévy noise is studied. The least squares estimator is proved to be asymptotic consistent in the case ε→0 and n→∞, and the asymptotic distribution of the estimator is obtained. Finally, the numerical simulation for the estimators of the competitive model is given, and the results are in line with the theory.

Key words: Lotka-Volterra model, Lévy noise, least squares estimator, asymptotic consistency

中图分类号: 

  • O211.63

表1

(ε1, ε2)=(0.05, 0.05)时, 未知参数的LSE和AE"

真值 n=500 n=2 000 n=5 000
LSE AE LSE AE LSE AE
b1=0.8 0.828 9 0.028 9 0.822 2 0.022 2 0.812 7 0.012 7
a11=0.7 0.795 3 0.095 3 0.736 2 0.036 2 0.716 1 0.016 1
a12=0.4 0.383 1 0.016 9 0.402 4 0.002 4 0.402 3 0.002 3
b2=0.9 0.983 0 0.083 0 0.922 4 0.022 4 0.910 7 0.010 7
a21=0.4 0.366 2 0.033 8 0.392 0 0.008 0 0.392 7 0.002 8
a22=0.6 0.682 6 0.082 6 0.620 1 0.020 1 0.608 2 0.008 2

表2

(ε1, ε2)=(0.01, 0.01)时, 未知参数的LSE和AE"

真值 n=500 n=2 000 n=5 000
LSE AE LSE AE LSE AE
b1=0.8 0.780 8 0.019 2 0.797 1 0.002 9 0.801 1 0.001 1
a11=0.7 0.715 0 0.015 0 0.710 4 0.010 4 0.707 1 0.007 1
a12=0.4 0.377 4 0.022 6 0.393 3 0.006 7 0.398 0 0.002 0
b2=0.9 0.939 4 0.039 4 0.917 2 0.017 2 0.907 1 0.007 1
a21=0.4 0.388 1 0.011 9 0.395 9 0.004 1 0.397 7 0.002 3
a22=0.6 0.638 0 0.038 0 0.616 0 0.016 0 0.606 8 0.006 8

表3

(ε1, ε2)=(0.005, 0.005)时, 未知参数的LSE和AE"

真值 n=500 n=2 000 n=5 000
LSE AE LSE AE LSE AE
b1=0.8 0.789 8 0.010 2 0.795 7 0.004 3 0.799 4 0.000 6
a11=0.7 0.704 8 0.004 8 0.703 5 0.003 5 0.703 2 0.003 2
a12=0.4 0.389 4 0.010 6 0.395 0 0.005 0 0.398 2 0.001 8
b2=0.9 0.917 6 0.017 6 0.910 6 0.010 6 0.906 2 0.006 2
a21=0.4 0.396 4 0.003 6 0.397 5 0.002 5 0.398 9 0.001 1
a22=0.6 0.616 3 0.016 3 0.609 8 0.009 8 0.605 6 0.005 6

图1

参数估计的正态QQ图"

1 WEI Chao . Parameter estimation for stochastic Lotka-Volterra model driven by small Lévy noises from discrete observations[J]. Communications in Statistics: Theory and Methods, 2021, 50 (24): 6014- 6023.
doi: 10.1080/03610926.2020.1738489
2 APPLEBAUM D . Lévy processes and stochastic calculus[M]. Cambridge: Cambridge University Press, 2009: 100- 131.
3 BAO J H , MAO X R , YIN G , et al. Competitive Lotka-Volterra population dynamics with jumps[J]. Nonlinear Analysis: Theory, Methods & Applications, 2011, 74 (17): 6601- 6616.
4 马永刚, 张启敏, 刘俊梅. 具有随机扰动的Lotka-Volterra竞争模型的参数估计[J]. 数学杂志, 2018, 38 (2): 367- 374.
MA Yonggang , ZHANG Qimin , LIU Junmei . Parameter estimation for Lotka-Volterra competition model with random perturbations[J]. Journal of Mathematics, 2018, 38 (2): 367- 374.
5 蒋达清. 随机微分方程中的参数估计与假设检验问题[D]. 长春: 东北师范大学, 2006.
JIANG Daqing. Problems of estimation and hypothesis testing of parameters in stochastic differential equations[D]. Changchun: Northeast Normal University, 2006.
6 LIU Meng , WANG Ke . Stochastic Lotka-Volterra systems with Lévy noise[J]. Journal of Mathematical Analysis and Applications, 2014, 410 (2): 750- 763.
doi: 10.1016/j.jmaa.2013.07.078
7 BAO Jianhai , YUAN Chenggui . Stochastic population dynamics driven by Lévy noise[J]. Journal of Mathematical Analysis and Applications, 2012, 391 (2): 363- 375.
doi: 10.1016/j.jmaa.2012.02.043
8 ZHAO Huiyan , ZHANG Chongqi , WEN Limin . Maximum likelihood estimation for stochastic Lotka-Volterra model with jumps[J]. Advances in Difference Equations, 2018, 148 (1): 1- 22.
9 WEI Chao , WEI Yan , ZHOU Yingying . Least squares estimation for discretely observed stochastic Lotka-Volterra model driven by small α-stable noises[J]. Discrete Dynamics in Nature and Society, 2020, 2020 (1): 1- 11.
10 LONG Hongwei , MA Chunhua , SHIMIZU Y . Least squares estimators for stochastic differential equations driven by small Lévy noises[J]. Stochastic Processes and Their Applications, 2017, 127 (5): 1475- 1495.
doi: 10.1016/j.spa.2016.08.006
[1] 张翠芸,郭精军,马爱琴. 基于离散观测的次分数Vasicek模型的参数估计[J]. 《山东大学学报(理学版)》, 2023, 58(11): 15-26.
[2] 刘谢进1, 缪柏其2. 平衡损失函数下Bayes线性无偏最小方差估计的优良性[J]. J4, 2011, 46(11): 89-95.
[3] 周小双1,2. 错误先验指定下Bayes估计与广义最小二乘估计的相对效率[J]. J4, 2010, 45(9): 70-73.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
[1] 唐风琴1,白建明2. 一类带有广义负上限相依索赔额的风险过程大偏差[J]. J4, 2013, 48(1): 100 -106 .
[2] 程智1,2,孙翠芳2,王宁1,杜先能1. 关于Zn的拉回及其性质[J]. J4, 2013, 48(2): 15 -19 .
[3] 汤晓宏1，胡文效2*，魏彦锋2，蒋锡龙2，张晶莹2，. 葡萄酒野生酿酒酵母的筛选及其生物特性的研究[J]. 山东大学学报（理学版）, 2014, 49(03): 12 -17 .
[4] 冒爱琴1, 2, 杨明君2, 3, 俞海云2, 张品1, 潘仁明1*. 五氟乙烷灭火剂高温热解机理研究[J]. J4, 2013, 48(1): 51 -55 .
[5] 李永明1, 丁立旺2. PA误差下半参数回归模型估计的r-阶矩相合[J]. J4, 2013, 48(1): 83 -88 .
[6] 董丽红1,2,郭双建1. Yetter-Drinfeld模范畴上的弱Hopf模基本定理[J]. J4, 2013, 48(2): 20 -22 .
[7] 罗斯特,卢丽倩,崔若飞,周伟伟,李增勇*. Monte-Carlo仿真酒精特征波长光子在皮肤中的传输规律及光纤探头设计[J]. J4, 2013, 48(1): 46 -50 .
[8] 田学刚, 王少英. 算子方程AXB=C的解[J]. J4, 2010, 45(6): 74 -80 .
[9] 霍玉洪,季全宝. 一类生物细胞系统钙离子振荡行为的同步研究[J]. J4, 2010, 45(6): 105 -110 .
[10] 赵君1,赵晶2,樊廷俊1*,袁文鹏1,3,张铮1,丛日山1. 水溶性海星皂苷的分离纯化及其抗肿瘤活性研究[J]. J4, 2013, 48(1): 30 -35 .
版权所有 © 2018 《山东大学学报(理学版)》编辑部　
地址: 山东省济南市山大南路27号山东大学中心校区（250100）　电话: +86-0531-88366917　E-mail: xblxb@sdu.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发