A new online computer program (BiDASys) for ordinary and uncertainty weighted least-squares linear regressions: case studies from food chemistry

  • Mauricio Rosales-Rivera, M.Sc. Universidad Autónoma del Estado de Morelos
  • Lorena Díaz-González, Dr. Universidad Autónoma del Estado de Morelos
  • Surendra P Verma, Dr. Instituto de Energías Renovables, Universidad Nacional Autónoma de México

Abstract

A new computer program BiDASys (Bivariate Data Analysis System) is presented for the application of Ordinary and Uncertainty weighted least-squares linear regression models (OLR and UWLR) to experimental data from food chemistry. BiDASys has the following novel aspects: the statistical capability of detecting discordant outliers in bivariate data; new simulated critical values generated through our Monte Carlo simulation procedure for the probability of no-correlation in multivariate samples of sizes n=5–1000; and the only available software that can successfully achieve the application of the new UWLR model to the experimental data. The use of BiDASys is illustrated through three case studies from Glera-Prosecco (Italy), Quebec (Canada), and Tuscany to Basilicata (Italy), which confirms that the Sr isotopic ratio (87Sr/86Sr) can be used to track the geographical origin of wine (grapes plantation) and one more case study concerning the organochlorine pesticide levels in breast milk from Guerrero (Mexico).

Published
Feb 10, 2018
How to Cite
ROSALES-RIVERA, Mauricio; DÍAZ-GONZÁLEZ, Lorena; VERMA, Surendra P. A new online computer program (BiDASys) for ordinary and uncertainty weighted least-squares linear regressions: case studies from food chemistry. Revista Mexicana de Ingeniería Química, [S.l.], v. 17, n. 2, p. 507-522, feb. 2018. ISSN 2395-8472. Available at: <http://rmiq.org/ojs/index.php/rmiq/article/view/324>. Date accessed: 20 feb. 2018.
Section
Food Engineering

Received 2 November 2017, published online 10 February 2018