Abstract
NORMUL is a FORTRAN program that provides a test of whether data conform to a multivariate normal distribution. The method involves correlating Mahalanobis distances for observed data with expected chi-square percentile values. This obtained correlation is then tested for significance by empirically evaluating the probability of its belonging to a distribution generated from multivariate normal data.
Article PDF
Avoid common mistakes on your manuscript.
References
Blom, G. (1958).Statistical estimates and transformed beta variables. New York: Wiley.
Bradley, D. R. (1988).DATASIM [Computer program]. Lewiston, ME: Desktop Press.
International Mathematical and Statistical Libraries (1987).International Mathematical and Statistical Libraries reference manual (10th ed.). Houston: Author.
Johnson, R. A., &Wichern, D. W. (1992).Applied multivariate statistical analysis (3rd ed.). Englewood Cliffs, NJ: Prentice-Hall.
Looney, S. W., &Gulledge, T. R., Jr. (1985). Use of the correlation coefficient with normal probability plots.American Statistician,39, 75–79.
Stevens, J. (1992).Applied multivariate statistics for the social sciences (2nd ed.). Hillsdale, NJ: Erlbaum.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Holden, R.R., Parent, M. NORMUL: A FORTRAN program for testing multivariate normality. Behavior Research Methods, Instruments, & Computers 27, 400–403 (1995). https://doi.org/10.3758/BF03200436
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.3758/BF03200436