Minimax Estimator for linear models with nonrandom disturbances
This paper collects some results of the authors on minimax estimation of parameters in linear (regression) models disturbed by some nuisance parameters. In contrast to conventional modelling, the disturbances are not specified as random variables but rather as unknown parameters, for which some a priori knowledge may be available. For various models and under different a priori restrictions on parameters and disturbances, either explicit formulas for the linear minimax estimator are derived or characterizations in form of spectral equations are obtained.
|Date of creation:||Jan 1995|
|Date of revision:|
|Contact details of provider:|| Postal: Bonn Graduate School of Economics, University of Bonn, Adenauerallee 24 - 26, 53113 Bonn, Germany|
Fax: +49 228 73 6884
Web page: http://www.bgse.uni-bonn.de
Please report citation or reference errors to , or , if you are the registered author of the cited work, log in to your RePEc Author Service profile, click on "citations" and make appropriate adjustments.:
- Norbert Christopeit & Kurt Helmes, 1991. "On Minimax Estimation in Linear Regression Models with Ellipsoidal Constraints," Discussion Paper Serie B 205, University of Bonn, Germany.
When requesting a correction, please mention this item's handle: RePEc:bon:bonsfb:359. See general information about how to correct material in RePEc.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (BGSE Office)
If references are entirely missing, you can add them using this form.