MINIMAX TESTS FOR CONVEX CONES

被引:1
作者
DUMBGEN, L
机构
[1] Institut für Angewandte Mathematik, Universität Heidelberg, Heidelberg, D-69120
关键词
BIAS; CONVEX CONE; COVARIANCE MATRIX; DUALITY; LINEAR REGRESSION; MINIMAX TEST; UNION INTERSECTION PRINCIPLE;
D O I
10.1007/BF00773419
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
Let (P-theta : theta is an element of R(P)) be a simple shift, family of distributions on R(P), and let K subset of R(P) be a convex cone. Within the class of nonrandomized tests of K versus R(P)\K, whose acceptance region A satisfies A = A + K, a test with minimal bias is constructed. This minimax test is compared to a likelihood ratio type test, which is optimal with respect to a different criterion. The minimax test is mimicked in the context of linear regression and one-sided tests for covariance matrices.
引用
收藏
页码:155 / 165
页数:11
相关论文
共 8 条
[1]   LIKELIHOOD RATIO TESTS FOR COVARIANCE STRUCTURE IN RANDOM EFFECTS MODELS [J].
KURIKI, S .
JOURNAL OF MULTIVARIATE ANALYSIS, 1993, 46 (02) :175-197
[2]  
LEHMANN EL, 1986, TESTING STATISTICAL
[3]  
Robertson T., 1988, ORDER RESTRICTED STA
[4]  
Rockafellar R.T., 1970, CONVEX ANAL
[5]   THE ADMISSIBILITY OF HOTELLINGS T2-TEST [J].
STEIN, C .
ANNALS OF MATHEMATICAL STATISTICS, 1956, 27 (03) :616-623
[6]  
[No title captured]
[7]  
[No title captured]
[8]  
[No title captured]