Research Article

A Simple Empirical Likelihood Ratio Test for Normality Based on the Moment Constraints of a Half-Normal Distribution

Table 6

Results of the Monte Carlo power comparisons based on samples with sizes from symmetric alternative distributions defined on at .

Symmetric alternative distributions defined on at
Distribution AD CVMJB SW DB SEELR

Beta(2,2)200.05640.0544 0.05940.0052 0.0516 0.1310 0.06960.0970
300.07860.0520 0.0812 0.0012 0.0768 0.2004 0.05500.1962
500.12220.0852 0.11720.0010 0.1528 0.3468 0.06280.4252
800.23400.1256 0.18340.0128 0.3170 0.59780.1128 0.7204

Beta(3,3)200.04040.0474 0.04080.0076 0.0372 0.0780 0.05180.0620
300.07860.0520 0.08120.0046 0.0768 0.1112 0.03920.1030
500.07360.0524 0.06500.00140.0682 0.16540.03260.1906
800.10760.0762 0.08260.0022 0.1128 0.2772 0.02980.3458

Beta(0.5,0.5)200.61600.3098 0.50580.0066 0.7190 0.90940.70920.7015
300.85760.4998 0.73320.0052 0.9392 0.9914 0.8830 0.8960
500.99020.7976 0.95680.3822 0.9992 1.00000.9916 0.9956
801.00000.9724 0.9990 0.9872 1.0000 1.0000 1.0000 1.0000

Uniform(0,1)200.16400.1014 0.13960.0040 0.1886 0.4064 0.25980.3332
300.30040.1422 0.22620.0020 0.3894 0.6622 0.32020.6002
500.57800.2532 0.42820.0118 0.7546 0.9358 0.56240.9120
800.86360.4578 0.70920.3706 0.9688 0.99900.8730 0.9944

Logit-norm(0,1)200.06480.0442 0.05620.0056 0.0578 0.1294 0.07000.1010
300.08580.0574 0.07480.0024 0.0796 0.1974 0.06580.1990
500.13940.0812 0.12200.0010 0.1612 0.3420 0.06760.4156
800.26300.1368 0.21140.01260.3408 0.5830 0.10940.7108

Logit-norm(0,2)20 0.37580.18440.29340.00460.43660.70340.48060.5348
300.60920.28840.48220.0030 0.73420.91500.65120.8258
500.90160.54120.78140.1174 0.9742 0.99760.90060.9818
800.99420.81700.9644 0.85941.00001.00000.99580.9996

Anderson-Darling () test, Modified Kolmogorov-Smirnov () test [2], Cramer-von Mises test () test, Jarque-Bera () test, Shapiro-Wilk () test, density based empirical likelihood ratio based () test [16], simple and exact empirical likelihood ratio based () test [13], and the proposed test .