caa a22 4500 477076599 CHVBK 20180405111440.0 cr unu---uuuuu 170330e19960401xx s 000 0 eng 10.1007/BF00046996 doi (NATIONALLICENCE)springer-10.1007/BF00046996 Hypothesis testing using affine linear estimators [Elektronische Daten] [P. Stahlecker, H. Knautz, G. Trenkler] The general linear hypothesis is usually tested by means of anF-statistic dependent on the least squares estimator. In this paper, a class of linear estimators is identified which can also serve as a basis for such anF-statistic. Conditions are derived under which thisF-statistic coincides with the usual one. This opens the possibility of constructing minimax-estimators which dominate LS with respect to risk, yielding the same test results. Kluwer Academic Publishers, 1996 linear regression model nationallicence minimax estimation nationallicence linear estimators nationallicence F -test nationallicence Stahlecker P. Department of Economics, University of Hamburg, Germany aut Knautz H. Department of Economics, University of Hamburg, Germany aut Trenkler G. Department of Statistics, University of Dortmund, Germany aut Acta Applicandae Mathematica Kluwer Academic Publishers 43/1(1996-04-01), 153-158 0167-8019 43:1<153 1996 43 10440 https://doi.org/10.1007/BF00046996 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1007/BF00046996 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Stahlecker P. Department of Economics, University of Hamburg, Germany aut NATIONALLICENCE 700 1- Knautz H. Department of Economics, University of Hamburg, Germany aut NATIONALLICENCE 700 1- Trenkler G. Department of Statistics, University of Dortmund, Germany aut NATIONALLICENCE 773 0- Acta Applicandae Mathematica Kluwer Academic Publishers 43/1(1996-04-01), 153-158 0167-8019 43:1<153 1996 43 10440 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer