大学数学
大學數學
대학수학
COLLEGE MATHEMATICS
2010年
5期
21-28
,共8页
Poisson-Lindley回归%EM算法%诊断%广义Cook距离%局部影响分析
Poisson-Lindley迴歸%EM算法%診斷%廣義Cook距離%跼部影響分析
Poisson-Lindley회귀%EM산법%진단%엄의Cook거리%국부영향분석
Poisson-Lindley regression%EM algorithm%diagnostic%generalized cook distance%local influence
利用EM算法研究了来自于Lindley分布权重的混合Poisson模型,即Poisson-Lindley回归模型,从而利用基于完全数据似然函数的条件期望进行统计诊断和局部影响分析,得到了几个有用的诊断统计量,并用一个数值实例说明了所得统计量的有效性.
利用EM算法研究瞭來自于Lindley分佈權重的混閤Poisson模型,即Poisson-Lindley迴歸模型,從而利用基于完全數據似然函數的條件期望進行統計診斷和跼部影響分析,得到瞭幾箇有用的診斷統計量,併用一箇數值實例說明瞭所得統計量的有效性.
이용EM산법연구료래자우Lindley분포권중적혼합Poisson모형,즉Poisson-Lindley회귀모형,종이이용기우완전수거사연함수적조건기망진행통계진단화국부영향분석,득도료궤개유용적진단통계량,병용일개수치실례설명료소득통계량적유효성.
The EM algorithm is employed as a basis to study for the Poisson-lindley models by treating them as a mixed Poisson regression with the weights from the Lindley distributions. We present diagnostic and local influence method for Poisson-lindley models. Several diagnostic measures are obtained in both case-deletion model and local influence analysis based on the conditional expectation of the complete-data log-likelihood function in the EM algorithm. The crime data is given to illustrate the results.