Correlation coefficient;
Entropy;
Monte Carlo simulation;
Power of a test;
KULLBACK-LEIBLER INFORMATION;
D O I:
暂无
中图分类号:
O21 [概率论与数理统计];
C8 [统计学];
学科分类号:
020208 ;
070103 ;
0714 ;
摘要:
In this article goodness of fit tests for the Gumbel distribution with type II right censored data are proposed. One test is based in earlier works using the Kullback Leibler information modified for censored data. The other tests are based on the sample correlation coefficient and survival analysis concepts. The critical values of the tests were obtained by Monte Carlo simulation for different sample sizes and percentages of censored data. The powers of the proposed tests were compared under several alternatives. The simulation results show that the test based on the Kullback-Leibler information is superior in terms of power to the correlation tests.
机构:Universidade de Santiago de Compostela,Models of Optimization, Decision, Statistics and Applications Reseach Group (MODESTYA), Department of Statistics, Mathematical Analysis and Optimization
Wenceslao González Manteiga
Cédric Heuchenne
论文数: 0引用数: 0
h-index: 0
机构:Universidade de Santiago de Compostela,Models of Optimization, Decision, Statistics and Applications Reseach Group (MODESTYA), Department of Statistics, Mathematical Analysis and Optimization
Cédric Heuchenne
César Sánchez Sellero
论文数: 0引用数: 0
h-index: 0
机构:Universidade de Santiago de Compostela,Models of Optimization, Decision, Statistics and Applications Reseach Group (MODESTYA), Department of Statistics, Mathematical Analysis and Optimization
César Sánchez Sellero
Alessandro Beretta
论文数: 0引用数: 0
h-index: 0
机构:Universidade de Santiago de Compostela,Models of Optimization, Decision, Statistics and Applications Reseach Group (MODESTYA), Department of Statistics, Mathematical Analysis and Optimization