Research Article

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

Table 7

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

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

Exp(1)200.78500.5722 0.72220.6230 0.8334 0.8384 0.8522 0.3642
300.92960.7780 0.89220.8286 0.9646 0.97540.99960.4752
500.99720.9594 0.98780.9756 0.9998 0.9992 1.00000.6400
801.00000.9990 0.99980.9998 1.0000 1.0000 1.0000 0.8114

Gamma(2,1)200.45900.3066 0.41360.4080 0.5380 0.44200.56840.2264
300.66620.4776 0.60720.5852 0.7502 0.6876 0.80940.2844
500.89600.6926 0.84360.8242 0.9500 0.9180 0.96680.3822
800.98400.8962 0.96820.9782 0.9976 0.9914 0.99840.5210

Lognorm(0,1)200.90800.7760 0.88460.8172 0.9350 0.9210 0.94180.6036
300.98380.9304 0.97300.9466 0.9888 0.9906 1.00000.7418
501.00000.9942 0.99980.9976 1.0000 1.0000 1.00000.9068
801.00001.0000 1.00001.0000 1.0000 1.00001.0000 0.9838

Lognorm(0,2)200.99860.9904 0.99700.9840 0.9990 0.9998 0.99990.8894
300.99980.9998 1.0000 0.9994 1.0000 1.0000 1.00000.9684
501.00001.0000 1.00001.0000 1.0000 1.00001.00000.9988
801.00001.0000 1.00001.0000 1.0000 1.0000 1.00001.0000

Weibull(2,1)200.13480.0980 0.11420.1258 0.15820.1264 0.16260.0932
300.18280.1306 0.16540.17040.2274 0.1958 0.27180.0892
500.30500.2000 0.25300.2738 0.4086 0.34460.52020.1120
800.49540.3186 0.42000.4346 0.6644 0.5634 0.7812 0.1080

Weibull(0.5,1)200.99620.98100.99540.95620.99900.99960.99860.8014
301.00000.9990 1.00000.99721.00001.00001.0000 0.9168
501.00001.00001.0000 1.00001.00001.00001.0000 0.9866
801.00001.00001.0000 1.00001.00001.00001.0000 1.0000

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 .