Abstract
Estimation accuracy of regression parameters with regard for inequality constraints and a forecast using the model obtained are compared with the least square estimation method. It is shown that the introduced constraints allows us to increase the estimation and forecasting accuracy.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
REFERENCES
A. S. Korkhin and M. I. Ginzburg, “Statistical properties of estimates by the least squares method given a priori inequality constraint,” Ekonomika i Mat. Metody, Issue 3, 496-506 (1987).
A. S. Korkhin, “Calculation of statistical properties of regression parameters estimates given a priori inequality constraints,” Ekonomika i Mat. Metody, Issue 2, 146-163 (1994).
E. Z. Demidenko, Linear and Nonlinear Regressions [in Russian], Financy i Statistika, Moscow (1981).
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Korkhin, A.S. Estimation Accuracy of Linear Regression Parameters with Regard for Inequalitiy Constraints Based on a Truncated Matrix of Mean Square Errors of Parameter Estimates. Cybernetics and Systems Analysis 38, 900–903 (2002). https://doi.org/10.1023/A:1022900206630
Issue Date:
DOI: https://doi.org/10.1023/A:1022900206630