![[PDF]](/pb-assets/Icons/adobe-pdf-icon-1498649896243.png){kind=icon}
Abstract
The power methods are simple and efficient algorithms used to generate either univariate or multivariate nonnormal distributions with specified values of (marginal) mean, standard deviation, skew, and kurtosis. The power methods are bounded as are other transformation techniques. Given an exogenous value of skew, there is an associated lower bound of kurtosis. Previous approximations of the boundary for the power methods are either incorrect or inadequate. Data sets from education and psychology can be found to lie within, near, or outside tile boundary of the power methods. In view of this, we derived necessary and sufficient conditions using the Lagrange multiplier method to determine the boundary of the power methods. The conditions for locating and classifying modes for distributions on the boundary were also derived. Self-contained interactive Fortran programs using a Weighted Simplex Procedure were employed to generate tabled values of minimum kurtosis for a given value of skew and power constants for various (non)normal distributions.
References
| Arrow, KJ, Enthoven, AC Quasi-Concave programmingEconometrica1961294779800 Google Scholar | Crossref | |
| Blair, RC A reaction to “Consequences of failure to meet assumptions underlying the fixed effects analysis of variance and covariance.”Review of Educational Research1981514499507 Google Scholar | SAGE Journals | |
| Blair, RC, Higgins, JJ A comparison of the power of Wilcoxon's rank-sum statistic to that of Student's t statistic under various non-normal distributionsJournal of Educational Statistics1980543093351980 Google Scholar | SAGE Journals | |
| Boneau, CA A comparison of the power of the U and t testsPsychological Review1962693246256 Google Scholar | Crossref | Medline | |
| Bradley, DR, Fleisher, CL Generating multivariate data from nonnormal distributions: Mihal and Barrett revisitedBehavior Research Methods, Instruments, & Computers1994262156166 Google Scholar | Crossref | |
| Bradley, JV Distribution free statistical tests1968Engelwood Cliffs, NJPrentice-Hall, 1968 Google Scholar | |
| Bradley, JV The insidious L-shaped distributionBulletin of the Psychonomic Society19822028588 Google Scholar | Crossref | |
| Chiang, AC Fundamental Methods of Mathematical Economics19843rd edNew YorkMcGraw-Hill Google Scholar | |
| Devroye, L Non-uniform random variate generation1986New YorkSpringer-Verlag Google Scholar | Crossref | |
| Fleishman, AI A method for simulating non-normal distributionsPsychometrika197843521532 Google Scholar | Crossref | |
| Glass, GV, Peckham, PD, Sanders, JR Consequences of failure to meet assumptions underlying the fixed effects analysis of variance and covarianceReview of Educational Research197242237288 Google Scholar | SAGE Journals | |
| Habib, AR, Harwell, MR An empirical study of the type I error rate and power of some selected normal theory and nonparametric tests of the independence of two sets of variablesCommunications in Statistics: Computation and Simulation1989182793826 Google Scholar | Crossref | |
| Harwell, MR, Serlin, RC An experimental study of a proposed test of nonparametric analysis of covariancePsychological Bulletin19881042268281 Google Scholar | Crossref | |
| Harwell, MR, Serlin, RC A nonparametric test statistic for the general linear modelJournal of Educational Statistics1989144351371 Google Scholar | SAGE Journals | |
| Harwell, MR, Serlin, RC An empirical study of five multivariate tests for the single-factor repeated measures modelCommunications in Statistics: Computation and Simulation1997262605618 Google Scholar | Crossref | |
| Headrick, TC Type I error and power of the rank transform analysis of covariance (ANCOVA) in a 3 × 4 factorial layout1997Detroit, MIWayne State UniversityUnpublished doctoral dissertation Google Scholar | |
| Headrick, TC, Sawilowsky, SS The best test for interaction in factorial ANOVA and ANCOVA1999JanuaryThe University of Florida Statistics Symposium on Selected Topics in Nonparametric MethodsGainesville, FL Google Scholar | |
| Headrick, TC, Sawilowsky, SS Simulating correlated multivariate nonnormal distributions: Extending the Fleishman power methodPsychometrika1999642535 Google Scholar | Crossref | |
| Hodges, JL, Lehmann, EL The efficiency of some nonparametric competitors of the t-testAnnals of Mathematical Statistics195627324335 Google Scholar | Crossref | |
| Kendall, M, Stuart, A The advanced theory of statistics19774th edNew YorkMacmillan Google Scholar | |
| Micceri, T The unicorn, the normal curve, and other improbable creaturesPsychological Bulletin1989105156166 Google Scholar | Crossref | |
| Olejnik, SF, Algina, J Parametric ANCOVA and the rank transform ANCOVA when the data are conditionally non-normal and heteroscedasticJournal of Educational Statistics198492129150 Google Scholar | SAGE Journals | |
| Olejnik, SF, Algina, J An analysis of statistical power for parametric ANCOVA and rank transform ANCOVACommunications in Statistics: Theory and Methods198716719231949 Google Scholar | Crossref | |
| Pearson, ES, Please, NW Relation between the shape of population distribution and the robustness of tour simple test statisticsBiometrika197563223241 Google Scholar | Crossref | |
| Price, WL A weighted simplex procedure for the solution of simultaneous nonlinear equationsJournal of the Institute of Mathematics and its Applications19792418 Google Scholar | Crossref | |
| Price, WL, Dowson, M Algorithm 107: A weighted simplex procedure for the solution of simultaneous nonlinear equationsThe Computer Journal197922222223 Google Scholar | |
| Ramberg, JS, Schmeiser, BW An approximate method for generating asymmetric random variablesCommunications of the ACM1974177882 Google Scholar | Crossref | |
| Rhee, K A FORTRAN solution for evaluating the coefficients of the power method for nonnormal transformationEducational and Psychological Measurement199353107109 Google Scholar | SAGE Journals | |
| Sawilowsky, SS, Blair, RC A more realistic look at the robustness and type I error properties of the t-test to departures from population normalityPsychological Bulletin19921112352360 Google Scholar | Crossref | |
| Scheffe, H The analysis of variance1959New YorkJohn Wiley & Sons Google Scholar | |
| Seamen, S, Algina, J, Olejnik, SF Type I error probabilities and power of the rank and parametric ANCOVA proceduresJournal of Educational Statistics1985104345367 Google Scholar | |
| Tadikamalla, PR On simulating nonnormal distributionsPsychometrika198045273279 Google Scholar | Crossref | |
| Tukey, JW The practical relationship between the common transformation of percentages of counts and of amounts1960Princeton, NJPrinceton University, Statistical Techniques Research Group(Technical Report 36) Google Scholar | |
| Visual Numerics, Inc IMSL Math/Library: FORTRAN subroutines for mathematical applications1994Volume IIHouston, TXAuthor Google Scholar |
