System Regularity Criterion of GMDH For Modelling in the Class of Regression Equations Systems with Random Coefficients. Alexander Sarychev

Abstract. The problem of search of optimum complexity system of regression equations with random coefficients by principles of the Group Method of Data Handling is considered. The criterion of quality of a system of regression equations that is system analogue of criterion of the regularity is offered. The criterion is researched in the scheme of repeated observations.

Keywords. Group Method of Data Handling, Criterion of the regularity for regression equations system with random coefficients, Repeated observations scheme.

References.

1. Sarychev A.P., Identification of Systems of Regression Models with Random Coefficients, Problems of Control and Informatics (Ukraine), 3, 16-32 (2004) (Journal of Automation and Information Sciences, Vol. 36, 5, 10-25 (2004)).
   
2. Sarychev A.P., Identification of Systems of Regression Models with Random Depended Coefficients. A Case of Covariance Matrix, Known to Within Scalar Parameter, Problems Applied Mathematics and Mathematical Modeling, DNU, Dnipropetrobsk (Ukraine), 290-302 (2007).
   
3. Sarychev A.P., Modeling in Class of Regression Equations Systems with Random Coefficients in Structural Uncertainty Conditions, Problems of Control and Informatics (Ukraine), 2, 27-41 (2008) (Journal of Automation and Information Sciences, Vol. 40, 3 (2008)).