The method of plotting probits against ranked data to obtain scatter plots is a simple, intuitive strategy for determining whether data are approximately normally distributed. A simple graphical technique is illustrated to obtain transformations used to acquire approximately normally distributed data. The method can be implemented on a MacIntosh or PC compatible computer running spread-sheet software with plotting capability.
Get full access to this article
View all access options for this article.
References
1.
Johnson, P. 0. (1949). Statistical methods in research. New York, NY: Prentice-Hall.
2.
Morgan, J. (1992). Personal Communication, Department of Mathematics, Texas A&M University.
3.
Rummel, R. J. (1970). Applied factor analysis. Evanston: North- western University Press.
4.
Shapiro, S. (1986). Volume 3: How to test normality and other distributional assumptions. Milwaukee, Wisconsin: American Society for Quality Control.
5.
Stevens, J. (1986). Applied multivariate statistics for the social sciences. Hillsdale, NJ: Erlbaum.
