DIFFERENCE OF POWER TEST AND TYPE II ERROR (β) ON MARDIA MVN TEST, HENZE ZIKLER'S MVN TEST, AND ROYSTON'S MVN TEST USING MULTIVARIATE DATA ANALYSIS

multivariate normal test Mardia MVN test Henze Zikler's MVN test Royston's MVN test

Authors

  • Wahyul Anis
    wahyul.anis@fk.unair.ac.id
    Faculty of Medicine, Universitas Airlangga, 60132 Surabaya, East Java, Indonesia
  • Kuntoro Kuntoro Faculty of Public Health, Universitas Airlangga, 60115 Surabaya, East Java, Indonesia
  • Soenarnatalina Melaniani Faculty of Public Health, Universitas Airlangga, 60115 Surabaya, East Java, Indonesia
October 31, 2021

Downloads

The Mardia MVN test, Henze Zikler's MVN test, and Royston's MVN test are the most widely used tests to analyze multivariate normal (MVN) data, but there have not been many studies explaining the advantages and disadvantages of these tests. The research objective was to analyze the difference in test strength and type II (β) error in the Mardia MVN test, Henze Zikler's MVN test, and Royston's MVN test. The research data were analyzed using three MVN tests, namely the Mardia MVN test, Henze Zikler's MVN test, and Royston's MVN test. The results of the analysis in the form of test strength and type II error (β) would be compared at alpha (α) 1%, 5%, 10%, 15%, 20%, and 25%. The comparison results explained that the Mardia test had the greatest test strength and the smallest type II (β) error. The study concluded that the Mardia MVN test was a multivariate normal test better than Henze Zikler's MVN test and Royston's MVN test.

Most read articles by the same author(s)

1 2 > >>