The general minimax estimator of the linear regression model is applicable when the whole parameter vector is restricted to an ellipsoid. In many applications, however, it is more realistic to assume that only a part of the parameter set is constrained. For this case an alternative minimax approach is developed. 4 1 (1 987). nr.2 9 0,l 0,5 1,0 10,O 100,O V 127 030 091 0.5 0,75 0,99 0,263 0,259 0,172 0,087 0,001 0,363 0,355 '0,242 0,142 0,004 0,464 0,455 0,327 0,213 0,008 0,862 0,855 0,780 0,702 0,116 0,983 0,982 0,973 0,961 0,629
Statistica Neerlandica