Communications for Statistical Applications and Methods

The Korean Statistical Society (한국통계학회)
권호 표지

On the Fitting ANOVA Models to Unbalanced Data

  • Jong-Tae Park (Department of Mathematics, KAIST, Gusung-dong, Yusung-gu, Taejon, 305-701, KOREA) ;
  • Jae-Heon Lee (Department of Mathematics, KAIST, Gusung-dong, Yusung-gu, Taejon, 305-701, KOREA) ;
  • Byung-Chun Kim (Department of Mathematics, KAIST, Gusung-dong, Yusung-gu, Taejon, 305-701, KOREA)
  • Published : 1995.04.01
Download PDF
⟨ Previous Next ⟩

Abstract

A direct method for fitting analysis-of-variance models to unbalanced data is presented. This method exploits sparsity and rank deficiency of the matrix and is based on Gram-Schmidt orthogonalization of a set of sparse columns of the model matrix. The computational algorithm of the sum of squares for testing estmable hyphotheses is given.

Keywords

References

  1. Commnication in Statistics, Simulation v.16 Sparse matrices and the estimation of variance components by likelihood methods Feller,W.H.
  2. Journal of institute of Mathematical Applications v.12 Least squares computations by Givens transformations without squre roots Gentleman,W.M.
  3. Linear Algebra and its Applications v.10 Error analysis of QR decompositions by Givens transformations Gentleman,W.M.
  4. Linear Algebra and its Applications v.34 Solution of sparse least squares problems using Givens rotations George,J.A.;Heath,M.T.
  5. Journal of the American Statistical Association v.77 Nonorthogonal analysis of variance using a generalized congugate-gradient algorithm Golub,G.H.;Nash,S.G.
  6. SIAM Journal of Science and Statistical Computing v.3 Some extensions of an algorithm for sparse linear least squares problems Heath,M.T.
  7. SIAM Journal of Science and Statistical Computing v.5 Numerical methods for large sparse linear least squares problems Heath,M.T.
  8. Journal of ACM v.11 Algebraic specification of statistical models for analysis of variance computations Hemmerle,W.J.
  9. Journal of the American Statistical Association v.83 Nonorthogonal analysis variance using gradient methods Jamshidian,M.;Jennrich,R.I.
  10. Statistical Computing Kennedy,W.J.Jr.;Gentle,J.E.
  11. Proceeding of Statistical Computing Section A new congugate gradient algorithm for analysis of variance computations Kim,B.C.;Marasinghe,M.G.;Kennedy,W.J.Jr.
  12. American Statistician v.30 The use of R()-notation with unbalanced data Speed,F.M.;Hocking,R.R.