Premium
Reactivity Ratio Estimation in Non‐Linear Polymerization Models using Markov Chain Monte Carlo Techniques and an Error‐In‐Variables Framework
Author(s) -
Mathew Manoj,
Duever Thomas
Publication year - 2015
Publication title -
macromolecular theory and simulations
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.37
H-Index - 56
eISSN - 1521-3919
pISSN - 1022-1344
DOI - 10.1002/mats.201500017
Subject(s) - markov chain monte carlo , monte carlo method , markov chain , mathematics , linear regression , computer science , nonlinear regression , regression analysis , mathematical optimization , statistics
Reactivity ratio estimation was carried out in various nonlinear models using Markov Chain Monte Carlo (MCMC) technique and an error‐in‐variables (EVM) regression model. The implementation steps for three different polymerization case studies are discussed in detail and the results from this work are compared to previously used approximation methods. Approximation techniques that rely on linear regression theory are shown to produce inaccurate joint confidence regions (JCRs). Therefore, in this paper, we explore MCMC techniques that can be used to produce JCRs with correct shape and probability content. In addition, the paper illustrates how an EVM model can be used in tackling any type of regression problem, including multi‐response problems.