The ANOVA F test can still be used in some balanced designs with unequal variances and nonnormal data

Journal of Statistical Planning and Inference

Volumn 126, Issue 2, 2004, Pages 413-422

  Bathke, Arne ^a  

^a UNIVERSITY OF KENTUCKY   (United States)

Author keywords

Analysis of variance; Heteroscedasticity; Nonnormality; Type I error robustness; Unequal variances

Indexed keywords

EID: 10044285245     PISSN: 03783758     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.jspi.2003.09.010     Document Type: Article

References (9)

1. Akritas M.G. The rank transform method in some two-factor designs J. Amer. Statist. Assoc. 85 1990 73-78
2. Akritas M.G. Arnold S.F. Asymptotics for analysis of variance when the number of levels is large J. Amer. Statist. Assoc. 95 2000 212-226
3. Akritas M.G. Papadatos N. 2001. Heteroskedastic one-way ANOVA and lack-of-fit tests. Under review
4. Anderson T.W. An Introduction to Multivariate Statistical Analysis 1984 Wiley New York
5. Arnold S.F. The Theory of Linear Models and Multivariate Analysis 1981 Wiley New York
6. Bathke A. ANOVA for a large number of treatments Math. Methods Statist. 11 1 2002 118-132
7. Boos D.D. Brownie C. ANOVA and rank tests when the number of treatments is large Statist. Probab. Lett. 23 1995 183-191
8. Kotz S. Johnson N.C. (Eds.), 1986. In: Tan, W.Y. (Ed.) Encyclopedia of Statistical Sciences. Quadratic Forms, Vol. 7. Wiley, New York, pp. 375-379
9. Tan W.Y. Cheng S.S. Cumulants of bilinear forms and quadratic forms and their applications Commun. Statist. Theory Methods A 10 3 1981 283-298