×

Effects on the generalized Box-Cox transformation on type I error rate and power of Hotelling’s \(T^2\). (English) Zbl 1059.62058

Summary: Most multivariate statistical techniques rely on the assumption of multivariate normality. The effects of nonnormality on multivariate tests are assumed to be negligible when variance-covariance matrices and sample sizes are equal. Therefore, in practice, investigators usually do not attempt to assess multivariate normality.
In this simulation study, the effects of skewed and leptokurtic multivariate data on the Type I error and power of Hotelling’s \(T^2\) were examined by manipulating distribution, sample size, and variance-covariance matrix. The empirical Type I error rate and power of Hotelling’s \(T^2\) were calculated before and after the application of the generalized Box-Cox transformation. The findings demonstrated that even when variance-covariance matrices and sample sizes are equal, small to moderate changes in power still can be observed.

MSC:

62H15 Hypothesis testing in multivariate analysis
65C60 Computational problems in statistics (MSC2010)
65C05 Monte Carlo methods
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Tukey JW, Exploratory Data Analysis (1977)
[2] Hoyle MH, International Statistical Review 41 pp 203– (1973) · Zbl 0267.62005
[3] Box GEP, Annals of Mathematical Statistics 25 pp 290– (1954) · Zbl 0055.37305
[4] Tiku ML, Journal of the American Statistical Association 66 pp 913– · Zbl 0236.62051
[5] Harwell M, Journal of Educational Statistics 17 pp 315– (1992)
[6] Glass GV, Review of Educational Research 42 pp 237– (1972)
[7] Hopkins JW, Journal of the American Statistical Association 58 pp 1048– (1963)
[8] Mardia KV, Biometrika 58 pp 105– (1971) · Zbl 0218.62081
[9] Olson CL, Journal of the American Statistical Association 69 pp 894– (1974) · Zbl 0302.62026
[10] Box GEP, Journal of the Royal Statistical Society B 26 pp 211– (1964)
[11] Box GEP, Journal of the American Statistical Association 77 pp 209– (1982) · Zbl 0504.62058
[12] Box GEP, Statistics for Experimenters (1978)
[13] Emerson JD, Journal of the American Statistical Association 77 pp 103– (1982)
[14] Hines WGS, American Statistician 41 pp 21– (1987)
[15] Hinkley D, Applied Statistics 26 pp 67– (1977)
[16] Rode RA, American Statistician 42 pp 23– (1988)
[17] Andrews DF, Biometrics 27 pp 825– (1971)
[18] Andrews DF, Multivariate Analysis pp pp. 95–116– (1973)
[19] Hernandez F, Journal of the American Statistical Association 75 pp 855– (1980) · Zbl 0459.62028
[20] Cohen J, Statistical Power Analysis for the Behavioral Sciences (1988)
[21] Timm NH, Applied Multivariate Analysis (2002)
[22] PSYCHINFO: Psvcholoical Information Database (1983)
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.