The unicorn, the normal curve, and other improbable creatures.

Abstract

An investigation of the distributional characteristics of 440 large-sample achievement and psychometric measures found all to be significantly nonnormal at the alpha .01 significance level. Several classes of contamination were found, including tail weights from the uniform to the double exponential, exponential-level asymmetry, severe digit preferences, multimodalities, and modes external to the mean/median interval. Thus, the underlying tenets of normality-assuming statistics appear fallacious for these commonly used types of data. However, findings here also fail to support the types of distributions used in most prior robustness research suggesting the failure of such statistics under nonnormal conditions. A reevaluation of the statistical robustness literature appears appropriate in light of these findings.

Cites (1)

1. Consequences of Failure to Meet Assumptions Underlying the Fixed Effects Analyses of Variance and Covariance
   Glass, Gene V, Peckham, Percy D., Sanders, James R. · 1972 · Review of Educational Research

Show all 1 references

Cited by (36)

1. The robustness of test statistics to nonnormality and specification error in confirmatory factor analysis.
   Curran, Patrick J., West, Stephen G., Finch, John F. · 1996 · Psychological Methods
2. Principles and practice in reporting structural equation analyses.
   McDonald, Roderick P., Ho, Moon-Ho Ringo · 2002 · Psychological Methods
3. Confirmatory factor analysis with ordinal data: Comparing robust maximum likelihood and diagonally weighted least squares
   Li, Cheng-Hsien · 2016 · Behavior Research Methods
4. An empirical comparison of the efficacy of covariance-based and variance-based SEM
   Reinartz, Werner, Haenlein, Michael, Henseler, Jörg · 2009 · International Journal of Research in Marketing
5. Exploratory Factor Analysis: A Guide to Best Practice
   Watkins, Marley W. · 2018 · Journal of Black Psychology

See all 1,485