Literature DB >> 23894226

A New F Approximation for the Pillai-Bartlett Trace under H0.

Keith E Muller1.   

Abstract

Pillai suggested two approximations for the Pillai-Bartlett trace statistic in the null case. The first one matches one moment of a β1 random variable, and corresponds to an F random variable, and the second matches four moments in the Pearson system. Although intuitively appealing and widely used in current statistical packages, the first lacks accuracy even with moderate sample size. The second matches two moment ratios in the Pearson system and provides much greater accuracy. Two new approximations match two moments of a β1 random variable, and hence correspond to an F random variable, yet achieve most of the accuracy of Pillai's second approximation. The second of the two new approximations provides the best combination of logical properties and numerical accuracy.

Keywords:  Multivariate linear models; Repeated measures

Year:  1998        PMID: 23894226      PMCID: PMC3721183     

Source DB:  PubMed          Journal:  J Comput Graph Stat        ISSN: 1061-8600            Impact factor:   2.302


  1 in total

1.  Power Calculations for General Linear Multivariate Models Including Repeated Measures Applications.

Authors:  Keith E Muller; Lisa M Lavange; Sharon Landesman Ramey; Craig T Ramey
Journal:  J Am Stat Assoc       Date:  1992-12-01       Impact factor: 5.033

  1 in total
  3 in total

1.  GLIMMPSE: Online Power Computation for Linear Models with and without a Baseline Covariate.

Authors:  Sarah M Kreidler; Keith E Muller; Gary K Grunwald; Brandy M Ringham; Zacchary T Coker-Dukowitz; Uttara R Sakhadeo; Anna E Barón; Deborah H Glueck
Journal:  J Stat Softw       Date:  2013-09       Impact factor: 6.440

2.  POWERLIB: SAS/IML Software for Computing Power in Multivariate Linear Models.

Authors:  Jacqueline L Johnson; Keith E Muller; James C Slaughter; Matthew J Gurka; Matthew J Gribbin; Sean L Simpson
Journal:  J Stat Softw       Date:  2009-04-01       Impact factor: 6.440

3.  New Method Application for Marker-Trait Association Studies in Plants: Partial Least Square Regression Aids Detection of Simultaneous Correlations.

Authors:  Eliane Thaines Bodah; Bruce Weir
Journal:  Agric Res Technol       Date:  2017-12-15
  3 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.