Comparison of Tests for Univariate Normality
by Edith Seier
Tests for univariate normality, some of them not included in previous comparisons, are compared according to their power and simplicity, the validity of their reported p-values, their behavior under rounding, the information they provide and their availability in software. The power of each test was estimated by computer simulation for small, moderate and large sample sizes and a wide range of symmetric, skewed, contaminated and mixed distributions. A new omnibus test based on skewness and kurtosis is discussed.
skewness, kurtosis, L-skewness, scale contaminated, mixed distributions
READING THE ARTICLE: You can read the article in
portable document (.pdf) format (131940 bytes.)
NOTE: The content of this article is the intellectual property of the authors, who retains all rights to future publication.
This page has been accessed 4427 times since July 24, 2006.
Return to the Home Page.