Assessing the Accuracy of Mixture Model Regression Calculations
- 1 April 1982
- journal article
- research article
- Published by Taylor & Francis in Journal of Quality Technology
- Vol. 14 (2) , 67-79
- https://doi.org/10.1080/00224065.1982.11978792
Abstract
The Scheffé and Becker models for mixture systems present special computing problems because neither of these models contains a constant term. Scientists may find that the associated least-squares calculations are inaccurate because of computer roundoff errors or, worse yet, that the available regression program does not have the capability of fitting a zero-intercept model. It is shown that these two problems can be circumvented by dropping one of the linear terms from the model and replacing it with a constant term. The resulting intercept model produces all the coefficients, predictions and significance tests appropriate to the Scheffé or Becker models. Methods for detecting roundoff error are discussed and recommendations concerning preferred computing procedures are included. Examples illustrating the effectiveness of the proposed methodology are presented.Keywords
This publication has 5 references indexed in Scilit:
- Regression DiagnosticsPublished by Wiley ,1980
- Experimental designs for mixture systems with multicomponent constraintsCommunications in Statistics - Theory and Methods, 1979
- Models for the Response of a MixtureJournal of the Royal Statistical Society Series B: Statistical Methodology, 1968
- The Simplex-Centroid Design for Experiments with MixturesJournal of the Royal Statistical Society Series B: Statistical Methodology, 1963
- Experiments with MixturesJournal of the Royal Statistical Society Series B: Statistical Methodology, 1958