|
|
|
| Change point testing in logistic regression model based on empirical likelihood method |
| LI Yun-xia, LIU Wei-tang |
| School of Mathematics and Statistics, Zhejiang University of Finance and Economics, Hangzhou 310018, China |
|
|
|
Abstract A test and estimation of change point in Logistic regression model is discussed based on empirical likelihood method. The log-likelihood ratio test statistic is conducted by establishing a change-point model. In large-sample case, the empirical log-likelihood ratio test statistic is proved to have the same extreme value distribution as that with classical parametric log-likelihood. Under some mild conditions, the maximum empirical likelihood estimation of change point is also shown to be consistent. The simulation results and a real example demonstrate the feasibility of the proposed approach.
|
|
Received: 12 January 2015
Published: 27 May 2018
|
|
|
基于经验似然的Logistic回归模型的变点检验
基于经验似然对Logistic回归模型进行变点检验及估计. 通过建立变点模型, 构造经验对数似然比统计量, 在大样本下, 证明了经验对数似然比统计量与经典参数对数似然比统计量具有相同的极值分布, 同时得到变点的估计及估计的相合性, 并通过数值模拟及实例说明经验似然方法检验变点的可行性.
关键词：
变点,
经验似然,
Logistic回归,
极值分布,
相合性
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
| |
Shared |
|
|
|
|
| |
Discussed |
|
|
|
|
