Totally positive regression: E-optimal designs

被引:0
作者
Heiligers B. [1 ]
机构
[1] Fakultät für Mathematik, Inst. für Math. Stochastik, Universität Magdeburg
关键词
Approximate design; Chebyshev approximation; Chebyshev system; E-optimality; Equi-oscillation; Polynomial splines; Scalar optimality; Total positivity; Weighted polynomial regression;
D O I
10.1007/s184-002-8364-7
中图分类号
学科分类号
摘要
E-optimality of approximate designs in linear regression models is paired with a dual problem of nonlinear Chebyshev approximation. When the regression functions form a totally positive system, then the information matrices of designs for subparameters turn out to be "almost" totally positive, a property which allows to solve the nonlinear Chebyshev problem. Thereby we obtain explicit formulae for E-optimal designs in terms of equi-oscillating generalized polynomials. The considerations unify and generalize known results on E-optimality for particular regression setups.
引用
收藏
页码:191 / 213
页数:22
相关论文
共 42 条
  • [1] Ando T., Totally positive matrices, Lin Algebra Appl, 90, pp. 165-219, (1987)
  • [2] Anderson W.N., Shorted operators, SIAM J Appl Math, 20, pp. 520-525, (1971)
  • [3] Bellman R., Introduction to Matrix Analysis, (1960)
  • [4] DeBoor C., Pinkus A., The approximation of a totally positive band matrix by a strictly positive one, Lin Algebra Appl, 42, pp. 81-98, (1982)
  • [5] Carnicer J.M., Pena J.M., Totally positive bases for shape preserving curve design and optimality of B-splines, Computer Aided Geom Design, 11, pp. 633-654, (1994)
  • [6] Carnicer J.M., Pena J.M., Total positivity and optimal bases, Total Positivity and Its Applications, pp. 133-155, (1996)
  • [7] Chang F.-C., Heiligers B., E-optimal designs for polynomial regression without intercept, J Statist Plann Inference, 55, pp. 371-387, (1995)
  • [8] Cheney E.W., Introduction to Approximation Theory. (2nd. Edition), (1982)
  • [9] Dette H., A note on E-optimal designs for weighted polynomial regression, Ann Statist, 21, pp. 767-771, (1993)
  • [10] Dette H., Studden W.J., Geometry of E-optimality, Ann Statist, 21, pp. 416-433, (1993)