1
|
Moura MJ, Vertis CS, Redondo V, Oliveira NMC, Duarte BPM. Modeling the Batch Sedimentation of Calcium Carbonate Particles in Laboratory Experiments-A Systematic Approach. Materials (Basel) 2023; 16:4822. [PMID: 37445134 DOI: 10.3390/ma16134822] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/27/2023] [Revised: 06/26/2023] [Accepted: 06/30/2023] [Indexed: 07/15/2023]
Abstract
The design of continuous thickeners and clarifiers is commonly based on the solid flux theory. Batch sedimentation experiments conducted with solid concentrations still provide useful information for their application. The construction of models for the velocity of settling allows the estimation of the flux of solids throughout time, which can, in turn, be used to find the area of the units required to achieve a given solid concentration in the clarified stream. This paper addresses the numerical treatment of data obtained from batch sedimentation experiments of calcium carbonate particles. We propose a systematic framework to fit a model that is capable of representing the process features that involve (i) the numerical differentiation of data to generate initial estimates for the instantaneous velocity of settling; (ii) the integration of a differential equation to fit the model for the velocity of settling; and (iii) the assessment of the quality of the fit using common statistical indicators. The model used for demonstration has a theoretical basis combined with an empirical component to account for the effect of the particle concentrations and their state of aggregation. The values of the numerical parameters obtained are related to the characteristic dimensions of the aggregates and their mass-length fractal dimensions.
Collapse
Affiliation(s)
- Maria J Moura
- Instituto Politécnico de Coimbra, Instituto Superior de Engenharia de Coimbra, Rua Pedro Nunes, Quinta da Nora, 3030-199 Coimbra, Portugal
- Centro de Investigação em Engenharia dos Processos Químicos e dos Produtos da Floresta, Universidade de Coimbra, Rua Sílvio Lima, Pólo II, 3030-790 Coimbra, Portugal
| | - Carolina S Vertis
- Centro de Investigação em Engenharia dos Processos Químicos e dos Produtos da Floresta, Universidade de Coimbra, Rua Sílvio Lima, Pólo II, 3030-790 Coimbra, Portugal
| | - Vítor Redondo
- LED&MAT, Instituto Pedro Nunes, Rua Pedro Nunes, Edifício A, 3030-199 Coimbra, Portugal
| | - Nuno M C Oliveira
- Centro de Investigação em Engenharia dos Processos Químicos e dos Produtos da Floresta, Universidade de Coimbra, Rua Sílvio Lima, Pólo II, 3030-790 Coimbra, Portugal
| | - Belmiro P M Duarte
- Instituto Politécnico de Coimbra, Instituto Superior de Engenharia de Coimbra, Rua Pedro Nunes, Quinta da Nora, 3030-199 Coimbra, Portugal
- Centro de Investigação em Engenharia dos Processos Químicos e dos Produtos da Floresta, Universidade de Coimbra, Rua Sílvio Lima, Pólo II, 3030-790 Coimbra, Portugal
| |
Collapse
|
2
|
Ingrez IBD, Ferreira PCN, Gameiro D, Duarte BPM. On the Design of Aqueous Emulsions of Colophony Resin. Polymers (Basel) 2023; 15:polym15071691. [PMID: 37050305 PMCID: PMC10096859 DOI: 10.3390/polym15071691] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/22/2023] [Revised: 03/23/2023] [Accepted: 03/25/2023] [Indexed: 03/31/2023] Open
Abstract
Companies regularly face market pressure to develop products faster but they also need to simultaneously incorporate technological constraints, sustainability trends, and customer requirements into their designs, which requires the use of systematic procedures. Firms that exploit natural resources and convert them into high-value products are among them. However, the literature on the application of such systematic approaches to products of this type remains scarce, as they often requrire extensive experimental plans involving the testing and optimization of multiple formulations. Here, we propose a systematic approach to the design of pine-resin-in-water emulsions, which can be used to fabricate pressure-sensitive adhesives. The strategy is customer-centric in the sense that the customers’ specifications are integrated into the decision-making tool used to assess the quality of the formulations obtained through experiments. This tool uses loss functions to assess satisfaction with individual quality characteristics and multi-attribute decision-making methods to integrate them into an overall quality metric. Our framework is aligned with industrial practices and consists of three sequential stages: (i) screening of primary factors; (ii) optimization of secondary factors; and (iii) assessment of the experimental repeatability of the formulations. In each of these stages, the decision-making tool is used to “drive” the process of finding the optimal formulation.
Collapse
Affiliation(s)
- Isa B. D. Ingrez
- Instituto Politécnico de Coimbra, Instituto Superior de Engenharia de Coimbra, Rua Pedro Nunes, Quinta da Nora, 3030-199 Coimbra, Portugal
| | - Paula C. N. Ferreira
- Instituto Politécnico de Coimbra, Instituto Superior de Engenharia de Coimbra, Rua Pedro Nunes, Quinta da Nora, 3030-199 Coimbra, Portugal
- Centro de Investigação em Engenharia dos Processos Químicos e dos Produtos da Floresta, Universidade de Coimbra, Rua Sílvio Lima, Pólo II, 3030-790 Coimbra, Portugal
| | - Davide Gameiro
- Kemi Pine Rosins Portugal, S.A., Zona Industrial de Cantanhede, Lote 122, 3060-197 Cantanhede, Portugal
| | - Belmiro P. M. Duarte
- Instituto Politécnico de Coimbra, Instituto Superior de Engenharia de Coimbra, Rua Pedro Nunes, Quinta da Nora, 3030-199 Coimbra, Portugal
- Centro de Investigação em Engenharia dos Processos Químicos e dos Produtos da Floresta, Universidade de Coimbra, Rua Sílvio Lima, Pólo II, 3030-790 Coimbra, Portugal
- Correspondence:
| |
Collapse
|
3
|
Duarte BPM, Moura MJ. Using rheological monitoring to determine the gelation kinetics of chitosan-based systems. Math Biosci Eng 2023; 20:1176-1194. [PMID: 36650807 DOI: 10.3934/mbe.2023054] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/17/2023]
Abstract
The modeling of polymeric reactions is a topic of large interest. The gelation reactions that may result from self-crosslinking or hybrid (agent based-) crosslinking are examples with interest specially in biomaterials applications. The composition of polymer entities during the reaction is hard to follow, and their concentration is not a good measure of the system dynamics. One alternative is monitoring the rheological behavior of the reacting mass, and relate the elastic modulus of the mixture with the rheological degree of conversion. In this paper we use rheological data to fit Malkin and Kulichikin (1996) [1] based models to describe the crosslinking of chitosan. First, the self-crosslinking of chitosan is considered. Then, the agent-based crosslinking reaction promoted by genipin is addressed. We use dynamical rheological data to fit the reaction models. The model fitting problem generated using Maximum Likelihood principle with heteroscedastic prediction error variance is formulated as a Dynamic Optimization problem and subsequently solved with a sequential approach. Parametric confidence regions are computed using the linear approximation of the covariance matrix at the optimum. Further, the parameters correlation matrix is also determined and used to qualitatively infer about the practical identifiability. The reaction order obtained for self-crosslinking kinetics is 1.3375 ± (0.0151) - approximately of first order -, and is 2.2402 ± (0.0373) for hybrid crosslinking (approximately of second order). In both cases we prove the error variance model is heteroskedastic and the model is identifiable. The approach proposed herein can be extended to other polymer systems.
Collapse
Affiliation(s)
- Belmiro P M Duarte
- Department of Chemical and Biological Engineering, Coimbra Engineering Academy, Polytechnic Institute of Coimbra, Rua Pedro Nunes, Quinta da Nora, 3030-199 Coimbra, Portugal
- Centro de Investigação em Engenharia dos Processos Químicos e dos Produtos da Floresta, Department of Chemical Engineering, University of Coimbra, Rua Sílvio Lima, Pólo II, 3030-790 Coimbra, Portugal
| | - Maria J Moura
- Department of Chemical and Biological Engineering, Coimbra Engineering Academy, Polytechnic Institute of Coimbra, Rua Pedro Nunes, Quinta da Nora, 3030-199 Coimbra, Portugal
- Centro de Investigação em Engenharia dos Processos Químicos e dos Produtos da Floresta, Department of Chemical Engineering, University of Coimbra, Rua Sílvio Lima, Pólo II, 3030-790 Coimbra, Portugal
| |
Collapse
|
4
|
Duarte BPM, Atkinson AC, Granjo JFO, Oliveira NMC. Optimal Design of Experiments for Implicit Models. J Am Stat Assoc 2022. [DOI: 10.1080/01621459.2020.1862670] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/22/2022]
Affiliation(s)
- Belmiro P. M. Duarte
- Department of Chemical and Biological Engineering, Instituto Politécnico de Coimbra, Instituto Superior de Engenharia de Coimbra, Coimbra, Portugal
- CIEPQPF, Department of Chemical Engineering, University of Coimbra, Coimbra, Portugal
| | | | - José F. O. Granjo
- CIEPQPF, Department of Chemical Engineering, University of Coimbra, Coimbra, Portugal
| | - Nuno M. C. Oliveira
- CIEPQPF, Department of Chemical Engineering, University of Coimbra, Coimbra, Portugal
| |
Collapse
|
5
|
Duarte BPM, Atkinson AC, Singh SP, Reis MS. Optimal design of experiments for hypothesis testing on ordered treatments via intersection-union tests. Stat Pap (Berl) 2022. [DOI: 10.1007/s00362-022-01334-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/18/2022]
|
6
|
Duarte BPM, Singh SP, Moura MJ. Optimal design of multivariate acceptance sampling plans by variables. J STAT COMPUT SIM 2022. [DOI: 10.1080/00949655.2022.2060223] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/18/2022]
Affiliation(s)
- Belmiro P. M. Duarte
- Department of Chemical and Biological Engineering, Coimbra Polytechnic, ISEC, Coimbra, Portugal
- CIEPQPF, Department of Chemical Engineering, University of Coimbra, Pólo II, Coimbra, Portugal
| | - Satya P. Singh
- Department of Mathematics, IIT Hyderabad, Sangareddy, India
- Department of Mathematics and Statistics, Indian Institute of Technology Kanpur, Kanpur, India
| | - Maria J. Moura
- Department of Chemical and Biological Engineering, Coimbra Polytechnic, ISEC, Coimbra, Portugal
- CIEPQPF, Department of Chemical Engineering, University of Coimbra, Pólo II, Coimbra, Portugal
| |
Collapse
|
7
|
Duarte BPM, Sagnol G. Approximate and exact optimal designs for $$2^k$$ factorial experiments for generalized linear models via second order cone programming. Stat Pap (Berl) 2020. [DOI: 10.1007/s00362-018-01075-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
|
8
|
Affiliation(s)
- Belmiro P. M. Duarte
- Department of Chemical and Biological Engineering, Coimbra Polytechnic, ISEC, Coimbra, Portugal
- CIEPQPF, Department of Chemical Engineering, University of Coimbra, Coimbra, Portugal
| | - José F. O. Granjo
- CIEPQPF, Department of Chemical Engineering, University of Coimbra, Coimbra, Portugal
| |
Collapse
|
9
|
Masoudi E, Holling H, Duarte BPM, Wong WK. A Metaheuristic Adaptive Cubature Based Algorithm to Find Bayesian Optimal Designs for Nonlinear Models. J Comput Graph Stat 2019. [DOI: 10.1080/10618600.2019.1601097] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/27/2022]
Affiliation(s)
- Ehsan Masoudi
- Department of Psychology, University of Münster, Münster, Germany
| | - Heinz Holling
- Department of Psychology, University of Münster, Münster, Germany
| | - Belmiro P. M. Duarte
- Department of Chemical and Biological Engineering, ISEC, Polytechnic Institute of Coimbra, Coimbra, Portugal
- CIEPQPF, Department of Chemical Engineering, University of Coimbra, Coimbra, Portugal
| | - Weng Kee Wong
- Department of Biostatistics, UCLA Fielding School of Public Health, Los Angeles, CA
| |
Collapse
|
10
|
Duarte BPM, Wong WK. Optimal design of multiple-objective Lot Quality Assurance Sampling (LQAS) plans. Biometrics 2018; 75:572-581. [PMID: 30488433 DOI: 10.1111/biom.13008] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/22/2017] [Accepted: 11/14/2018] [Indexed: 11/26/2022]
Abstract
Lot Quality Assurance Sampling (LQAS) plans are widely used for health monitoring purposes. We propose a systematic approach to design multiple-objective LQAS plans that meet user-specified type 1 and 2 error rates and targets for selected diagnostic accuracy metrics. These metrics may include sensitivity, specificity, positive predictive value, and negative predictive value in high or low anticipated prevalence rate populations. We use Mixed Integer Nonlinear Programming (MINLP) tools to implement our design methodology. Our approach is flexible in that it can directly generate classic LQAS plans that control error rates only and find optimal LQAS plans that meet multiple objectives in terms of diagnostic metrics. We give examples, compare results with the classic LQAS and provide an application using a malaria outcome indicator survey in Mozambique.
Collapse
Affiliation(s)
- Belmiro P M Duarte
- Centro de Investigação em Processos Químicos e Produtos da Floresta, Department of Chemical Engineering, University of Coimbra, Pólo II, R. Sílvio Lima, 3030-790 Coimbra, Portugal.,Department of Chemical and Biological Engineering, ISEC, Polytechnic Institute of Coimbra, R. Pedro Nunes, 3030-199 Coimbra, Portugal
| | - Weng Kee Wong
- Department of Biostatistics, Fielding School of Public Health, UCLA, 10833 Le Conte Ave., Los Angeles, California 90095-1772
| |
Collapse
|
11
|
Granjo JFO, Duarte BPM, Oliveira NMC. Systematic Development of Kinetic Models for the Glyceride Transesterification Reaction via Alkaline Catalysis. Ind Eng Chem Res 2018. [DOI: 10.1021/acs.iecr.7b05328] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
Affiliation(s)
- José F. O. Granjo
- CIEPQPF, Department of Chemical Engineering, University of Coimbra, Rua Sílvio Lima−Pólo II, 3030−790 Coimbra, Portugal
| | - Belmiro P. M. Duarte
- CIEPQPF, Department of Chemical Engineering, University of Coimbra, Rua Sílvio Lima−Pólo II, 3030−790 Coimbra, Portugal
- Instituto Politécnico de Coimbra, ISEC, Department of Chemical and Biological Engineering, Rua Pedro Nunes, Quinta da Nora, 3030−199 Coimbra, Portugal
| | - Nuno M. C. Oliveira
- CIEPQPF, Department of Chemical Engineering, University of Coimbra, Rua Sílvio Lima−Pólo II, 3030−790 Coimbra, Portugal
| |
Collapse
|
12
|
Oliver-Rodríguez B, Zafra-Gómez A, Reis MS, Duarte BPM, Verge C, de Ferrer JA, Pérez-Pascual M, Vílchez JL. Wide-range and accurate modeling of linear alkylbenzene sulfonate (LAS) adsorption/desorption on agricultural soil. Chemosphere 2015; 138:148-155. [PMID: 26070080 DOI: 10.1016/j.chemosphere.2015.05.085] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/11/2015] [Accepted: 05/19/2015] [Indexed: 06/04/2023]
Abstract
In this paper, rigorous data and adequate models about linear alkylbenzene sulfonate (LAS) adsorption/desorption on agricultural soil are presented, contributing with a substantial improvement over available adsorption works. The kinetics of the adsorption/desorption phenomenon and the adsorption/desorption equilibrium isotherms were determined through batch studies for total LAS amount and also for each homologue series: C10, C11, C12 and C13. The proposed multiple pseudo-first order kinetic model provides the best fit to the kinetic data, indicating the presence of two adsorption/desorption processes in the general phenomenon. Equilibrium adsorption and desorption data have been properly fitted by a model consisting of a Langmuir plus quadratic term, which provides a good integrated description of the experimental data over a wide range of concentrations. At low concentrations, the Langmuir term explains the adsorption of LAS on soil sites which are highly selective of the n-alkyl groups and cover a very small fraction of the soil surface area, whereas the quadratic term describes adsorption on the much larger part of the soil surface and on LAS retained at moderate to high concentrations. Since adsorption/desorption phenomenon plays a major role in the LAS behavior in soils, relevant conclusions can be drawn from the obtained results.
Collapse
Affiliation(s)
- B Oliver-Rodríguez
- Research Group of Analytical Chemistry and Life Sciences, Department of Analytical Chemistry, Faculty of Sciences, University of Granada, Campus of Fuentenueva, E-18071 Granada, Spain
| | - A Zafra-Gómez
- Research Group of Analytical Chemistry and Life Sciences, Department of Analytical Chemistry, Faculty of Sciences, University of Granada, Campus of Fuentenueva, E-18071 Granada, Spain.
| | - M S Reis
- CIEPQPF - Department of Chemical Engineering, University of Coimbra, Coimbra, Portugal
| | - B P M Duarte
- CIEPQPF - Department of Chemical Engineering, University of Coimbra, Coimbra, Portugal
| | - C Verge
- Cepsa Química, Avenida del Partenón 12, E-28042 Madrid, Spain
| | - J A de Ferrer
- Cepsa Química, Avenida del Partenón 12, E-28042 Madrid, Spain
| | - M Pérez-Pascual
- Cepsa Química, Avenida del Partenón 12, E-28042 Madrid, Spain
| | - J L Vílchez
- Research Group of Analytical Chemistry and Life Sciences, Department of Analytical Chemistry, Faculty of Sciences, University of Granada, Campus of Fuentenueva, E-18071 Granada, Spain
| |
Collapse
|
13
|
Oliver-Rodríguez B, Zafra-Gómez A, Reis MS, Duarte BPM, Verge C, de Ferrer JA, Pérez-Pascual M, Vílchez JL. Evaluation of Linear Alkylbenzene Sulfonate (LAS) behaviour in agricultural soil through laboratory continuous studies. Chemosphere 2015; 131:1-8. [PMID: 25765258 DOI: 10.1016/j.chemosphere.2015.02.037] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/08/2014] [Accepted: 02/13/2015] [Indexed: 06/04/2023]
Abstract
The behaviour of Linear Alkylbenzene Sulfonate (LAS) in agricultural soil is investigated in the laboratory using continuous-flow soil column studies in order to simultaneously analyze the three main underlying phenomena (adsorption/desorption, degradation and transport). The continuous-flow soil column experiments generated the breakthrough curves for each LAS homologue, C10, C11, C12 and C13, and by adding them up, for total LAS, from which the relevant retention, degradation and transport parameters could be estimated, after proposing adequate models. Several transport equations were considered, including the degradation of the sorbate in solution and its retention by soil, under equilibrium and non-equilibrium conditions between the sorbent and the sorbate. In general, the results obtained for the estimates of those parameters that were common to the various models studied (such as the isotherm slope, first order degradation rate coefficient and the hydrodynamic dispersion coefficient) were rather consistent, meaning that mass transfer limitations are not playing a major role in the experiments. These three parameters increase with the length of the LAS homologue chain. The study will provide the underlying conceptual framework and fundamental parameters to understand, simulate and predict the environmental behaviour of LAS compounds in agricultural soils.
Collapse
Affiliation(s)
- B Oliver-Rodríguez
- Research Group of Analytical Chemistry and Life Sciences, Department of Analytical Chemistry, Faculty of Sciences, University of Granada, Campus of Fuentenueva, E-18071 Granada, Spain
| | - A Zafra-Gómez
- Research Group of Analytical Chemistry and Life Sciences, Department of Analytical Chemistry, Faculty of Sciences, University of Granada, Campus of Fuentenueva, E-18071 Granada, Spain.
| | - M S Reis
- Department of Chemical Engineering, University of Coimbra, Coimbra, Portugal
| | - B P M Duarte
- Department of Chemical & Biological Engineering, Polytechnic Institute of Coimbra, Portugal
| | - C Verge
- Cepsa Química, Avenida del Partenón 12, E-28042 Madrid, Spain
| | - J A de Ferrer
- Cepsa Química, Avenida del Partenón 12, E-28042 Madrid, Spain
| | - M Pérez-Pascual
- Cepsa Química, Avenida del Partenón 12, E-28042 Madrid, Spain
| | - J L Vílchez
- Research Group of Analytical Chemistry and Life Sciences, Department of Analytical Chemistry, Faculty of Sciences, University of Granada, Campus of Fuentenueva, E-18071 Granada, Spain
| |
Collapse
|
14
|
Abstract
T-optimum designs for model discrimination are notoriously difficult to find because of the computational difficulty involved in solving an optimization problem that involves two layers of optimization. Only a handful of analytical T-optimal designs are available for the simplest problems; the rest in the literature are found using specialized numerical procedures for a specific problem. We propose a potentially more systematic and general way for finding T-optimal designs using a Semi-Infinite Programming (SIP) approach. The strategy requires that we first reformulate the original minimax or maximin optimization problem into an equivalent semi-infinite program and solve it using an exchange-based method where lower and upper bounds produced by solving the outer and the inner programs, are iterated to convergence. A global Nonlinear Programming (NLP) solver is used to handle the subproblems, thus finding the optimal design and the least favorable parametric configuration that minimizes the residual sum of squares from the alternative or test models. We also use a nonlinear program to check the global optimality of the SIP-generated design and automate the construction of globally optimal designs. The algorithm is successfully used to produce results that coincide with several T-optimal designs reported in the literature for various types of model discrimination problems with normally distributed errors. However, our method is more general, merely requiring that the parameters of the model be estimated by a numerical optimization.
Collapse
Affiliation(s)
- Belmiro P M Duarte
- GEPSI - PSE Group, CIEPQPF, Department of Chemical Engineering, University of Coimbra, Pólo II, R. Sílvio Lima, 3030-790 Coimbra, Portugal; Department of Chemical and Biological Engineering, ISEC, Polytechnic Institute of Coimbra, R. Pedro Nunes, 3030-199 Coimbra, Portugal
| | - Weng Kee Wong
- Department of Biostatistics, Fielding School of Public Health, UCLA, 10833 Le Conte Ave., Los Angeles, CA 90095-1772, USA
| | - Anthony C Atkinson
- Department of Statistics, London School of Economics, London WC2A 2AE, United Kingdom
| |
Collapse
|
15
|
Abstract
This paper uses semidefinite programming (SDP) to construct Bayesian optimal design for nonlinear regression models. The setup here extends the formulation of the optimal designs problem as an SDP problem from linear to nonlinear models. Gaussian quadrature formulas (GQF) are used to compute the expectation in the Bayesian design criterion, such as D-, A- or E-optimality. As an illustrative example, we demonstrate the approach using the power-logistic model and compare results in the literature. Additionally, we investigate how the optimal design is impacted by different discretising schemes for the design space, different amounts of uncertainty in the parameter values, different choices of GQF and different prior distributions for the vector of model parameters, including normal priors with and without correlated components. Further applications to find Bayesian D-optimal designs with two regressors for a logistic model and a two-variable generalised linear model with a gamma distributed response are discussed, and some limitations of our approach are noted.
Collapse
Affiliation(s)
- Belmiro P M Duarte
- Department of Chemical and Biological Engineering, ISEC, Polytechnic Institute of Coimbra, R. Pedro Nunes, 3030-199 Coimbra, Portugal ; GEPSI, CIEPQPF, Department of Chemical Engineering, University of Coimbra, R. Sílvio Lima, Pólo II, 3030-790 Coimbra, Portugal
| | - Weng Kee Wong
- Department of Biostatistics, Fielding School of Public Health, UCLA, 10833 Le Conte Ave., Los Angeles, CA 90095-1772, USA
| |
Collapse
|
16
|
|
17
|
Affiliation(s)
- Belmiro P. M. Duarte
- Instituto Superior de Engenharia de Coimbra, Quinta da Nora, 3030 Coimbra, Portugal, and Department of Chemical Engineering, University of Coimbra, Pólo II, Pinhal de Marrocos, 3030-290 Coimbra, Portugal
| | - Pedro M. Saraiva
- Instituto Superior de Engenharia de Coimbra, Quinta da Nora, 3030 Coimbra, Portugal, and Department of Chemical Engineering, University of Coimbra, Pólo II, Pinhal de Marrocos, 3030-290 Coimbra, Portugal
| |
Collapse
|