Accession Number : AD0653265

Title :   LEAST SQUARES ANALYSIS WITH A DYNAMIC MODEL.

Descriptive Note : Technical rept.,

Corporate Author : WISCONSIN UNIV MADISON DEPT OF STATISTICS

Personal Author(s) : Box,G. E. P. ; Jenkins,G. M. ; Wichern,D. W.

Report Date : MAR 1967

Pagination or Media Count : 24

Abstract : Frequently in the study of dynamic systems one is faced with estimating the parameters in a mathematical model. A typical example of the situation we have in mind might arise in the study of the dynamics of a chemical process. In such a case, the x's would be manipulated inputs such as temperatures and concentrations while the y would represent the observed system output. For example, y might be the concentration of a particular chemical product. Even in simple cases one may be involved in estimation difficulties due to the number of parameters and the nonlinearity of the situation. To determine whether existing non-linear estimation procedures could be used to obtain precise estimates of the parameters in a mathematical model, it was decided to run an experiment with manufactured data.

Descriptors :   (*LEAST SQUARES METHOD, MATHEMATICAL MODELS), CHEMICAL REACTIONS, CORRELATION TECHNIQUES, ITERATIONS, MATHEMATICS, THEORY

Subject Categories : Physical Chemistry
      Statistics and Probability

Distribution Statement : APPROVED FOR PUBLIC RELEASE