A Note About Model Selection and Hypothesis Test Procedure to Discriminate Poisson and Bell Models

被引:1
作者
Lemonte, Artur J. [1 ]
机构
[1] Univ Fed Rio Grande do Norte, Dept Estat, Natal, RN, Brazil
关键词
Akaike information criterion; Kullback-Leibler divergence; Model selection; Vuong test;
D O I
10.1007/s42519-022-00246-y
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
The Bell distribution was introduced recently in the statistical literature. This distribution can be very similar to the Poisson distribution, and so it is quite important to provide procedures to discriminate these models. In this paper, we consider the Vuong test procedure and the Akaike information criterion to do that. Monte Carlo simulation experiments are carried out to study the performance of this test procedure to discriminate these two models, and comparisons with the Akaike criterion are made. An application to real data is also considered for illustrative purposes.
引用
收藏
页数:18
相关论文
共 15 条
[1]   Zero-inflated Bell scan: A more flexible spatial scan statistic [J].
Abolhassani, Ali ;
Prates, Marcos O. ;
Castellares, Fredy ;
Mahmoodi, Safieh .
SPATIAL STATISTICS, 2020, 36
[2]   NEW LOOK AT STATISTICAL-MODEL IDENTIFICATION [J].
AKAIKE, H .
IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 1974, AC19 (06) :716-723
[3]  
[Anonymous], 2002, MODEL SEL MULTIMODEL
[4]  
Bell E.T., 1934, AM MATH MONTHLY, V41, P411, DOI DOI 10.2307/2300300
[5]   Exponential polynomials [J].
Bell, ET .
ANNALS OF MATHEMATICS, 1934, 35 :258-277
[6]   On the Bell distribution and its associated regression model for count data [J].
Castellares, Fredy ;
Ferrari, Silvia L. P. ;
Lemonte, Artur J. .
APPLIED MATHEMATICAL MODELLING, 2018, 56 :172-185
[7]  
CHEN WWS, 1981, BIOMETRICS, V37, P611
[8]   On the Lambert W function [J].
Corless, RM ;
Gonnet, GH ;
Hare, DEG ;
Jeffrey, DJ ;
Knuth, DE .
ADVANCES IN COMPUTATIONAL MATHEMATICS, 1996, 5 (04) :329-359
[9]  
COX DR, 1962, J ROY STAT SOC B, V24, P406
[10]  
Crawley M.J., 2012, R BOOK, DOI [DOI 10.1002/9781118448908, 10.1002/9781118448908]