Construction and selection of quantitative planning models — a general procedure illustrated with models for stock control

The paper investigates the process of quantitative model construction when for a particular realworld decision problem different quantitative models are available. It develops first some general features for constructing a model hierarchy comprising all quantitative models which should be taken into consideration. The main objective is an investigation into the selection process giving the best quantitative model for the particular decision problem at hand. This selection, however, can be performed in different ways possibly ending up with different models. A myopic selection principle is suggested which leads to a class of strategies. Different strategies within this class are discussed showing the complexity of the selection procedure. The investigations are illustrated using inventory models particularly stressing the role of cost parameters.     

Assessing the relative efficiency of decision making units using DEA models with weight restrictions

In models of data envelopment analysis (DEA), an optimal set of input and output weights is generally assumed to represent the assessed decision making unit (DMU) in the best light in comparison to all the other DMUs. The paper shows that this may not be correct if absolute weight bounds or some other weight restrictions are added to the model. A consequence may be that the model will underestimate the relative efficiency of DMUs. The incorporation of weight restrictions in a maximin DEA model is suggested. This model can be further converted to more operational forms, which are similar to the classical DEA models.     

Some relationships between fuzzy and random set-based classifiers and models

When designing rule-based models and classifiers, some precision is sacrificed to obtain linguistic interpretability. Understandable models are not expected to outperform black boxes, but usually fuzzy learning algorithms are statistically validated by contrasting them with black-box models. Unless performance of both approaches is equivalent, it is difficult to judge whether the fuzzy one is doing its best, because the precision gap between the best understandable model and the best black-box model is not known.In this paper we discuss how to generate probabilistic rule-based models and classifiers with the same structure as fuzzy rule-based ones. Fuzzy models, in which features are partitioned into linguistic terms, will be compared to probabilistic rule-based models with the same number of terms in every linguistic partition. We propose to use these probabilistic models to estimate a lower precision limit which fuzzy rule learning algorithms should surpass.     

Optimal robust insurance with a finite uncertainty set

Decision-makers who usually face model/parameter risk may prefer to act prudently by identifying optimal contracts that are robust to such sources of uncertainty. In this paper, we tackle this issue under a finite uncertainty set that contains a number of probability models that are candidates for the “true”, but unknown model. Various robust optimisation models are proposed, some of which are already known in the literature, and we show that all of them can be efficiently solved via Second Order Conic Programming (SOCP). Numerical experiments are run for various risk preference choices and it is found that for relatively large sample size, the modeler should focus on finding the best possible fit for the unknown probability model in order to achieve the most robust decision. If only small samples are available, then the modeler should consider two robust optimisation models, namely the Weighted Average Model or Weighted Worst-case Model, rather than focusing on statistical tools aiming to estimate the probability model. Amongst those two, the better choice of the robust optimisation model depends on how much interest the modeler puts on the tail risk when defining its objective function. These findings suggest that one should be very careful when robust optimal decisions are sought in the sense that the modeler should first understand the features of its objective function and the size of the available data, and then to decide whether robust optimisation or statistical inferences is the best practical approach.     

FLOODING ON THE EEL RIVER: SYSTEM THEORETIC TIME SERIES,TRANSFER FUNCTION TIME SERIES,AND STRUCTURAL MODEL FORECASTS

Three models are developed to forecast precipitation, stream flow, and suspended sediment load for the Middle Fork Eel River basin near Dos Rios, California. The models are a structural model, a transfer function time series model, and a multivariate time series model based on the ideas of linear systems theory. Monthly observations from 1961 through 1970 were used to specify and estimate the models, and their performance was evaluated using 36 observations from 1971 through 1973. The comparisons show that all of the models are able to simulate the general trend of the data fairly well but that the two time series models capture the detail better. The system theoretic time series model fares the best, providing consistently better forecasts of all three series. We conclude that this model would be valuable for use in planning water supply systems in the Eel River basin.     

How to choose the simulation model for computer experiments: a local approach

In many scientific areas, non‐stochastic simulation models such as finite element simulations replace real experiments. A common approach is to fit a meta‐model, for example a Gaussian process model, a radial basis function interpolation, or a kernel interpolation, to computer experiments conducted with the simulation model. This article deals with situations where more than one simulation model is available for the same real experiment, with none being the best over all possible input combinations. From fitted models for a real experiment as well as for computer experiments using the different simulation models, a criterion is derived to identify the locally best one. Applying this criterion to a number of design points allows the design space to be split into areas where the individual simulation models are locally superior. An example from sheet metal forming is analyzed, where three different simulation models are available. In this application and many similar problems, the new approach provides valuable assistance with the choice of the simulation model to be used. Copyright © 2011 John Wiley & Sons, Ltd.     

Supplier selection by the pair of nondiscretionary factors-imprecise data envelopment analysis models

Discretionary models for evaluating the efficiency of suppliers assume that all criteria are discretionary, that is, controlled by the management of each supplier and varied at its discretion. These models do not assume supplier selection in the conditions that some factors are nondiscretionary. The objective of this paper is to propose a new pair of nondiscretionary factors-imprecise data envelopment analysis (NF-IDEA) models for selecting the best suppliers in the presence of nondiscretionary factors and imprecise data. A numerical example demonstrates the application of the proposed method.     

Including sustainability criteria into inventory models

Research on sustainability performance has considerably enriched operations management literature in recent years. However, work with quantitative models is still scarce. This paper contributes by revisiting classical inventory methods taking sustainability concerns into account. We believe that reducing all aspects of sustainable development to a single objective is not desirable. We thus reformulate the classical economic order quantity model as a multiobjective problem. We refer to this model as the sustainable order quantity model. Then, a multi-echelon extension of the sustainable order quantity model is studied. For both models, the set of efficient solutions (Pareto optimal solutions) is analytically characterized. These results are used to provide some insights about the effectiveness of different regulatory policies to control carbon emissions. We also use an interactive procedure that allows the decision maker to quickly identify the best option among these solutions. The proposed interactive procedure is a new combination of multi-criteria decision analysis techniques.     

An interactive method of tackling uncertainty in interval multiple objective linear programming

Mathematical programming models for decision support must explicitly take account of the treatment of the uncertainty associated with the model coefficients along with multiple and conflicting objective functions. Interval programming just assumes that information about the variation range of some (or all) of the coefficients is available. In this paper, we propose an interactive approach for multiple objective linear programming problems with interval coefficients that deals with the uncertainty in all the coefficients of the model. The presented procedures provide a global view of the solutions in the best and worst case coefficient scenarios and allow performing the search for new solutions according to the achievement rates of the objective functions regarding both the upper and lower bounds. The main goal is to find solutions associated with the interval objective function values that are closer to their corresponding interval ideal solutions. It is also possible to find solutions with non-dominance relations regarding the achievement rates of the upper and lower bounds of the objective functions considering interval coefficients in the whole model.     

Determining optimal pollution control policies: An application of bilevel programming

This paper presents two optimization models for hazardous waste capacity planning and treatment facility locations. The complex behavior of firms in the presence of central planning decisions and price signals is investigated and it is shown that such behavior can best be captured by a hierarchical model. In particular, a central planning model, where the government is assumed to control all location/allocation decisions and a bilevel model, where the government is the leader with the goal of maximizing the `social welfare' via taxation is presented. Detailed formulations of both models are developed, solved, and the computational results are presented.     

Combining an Additive and Tree-Based Regression Model Simultaneously: STIMA

Additive models and tree-based regression models are two main classes of statistical models used to predict the scores on a continuous response variable. It is known that additive models become very complex in the presence of higher order interaction effects, whereas some tree-based models, such as CART, have problems capturing linear main effects of continuous predictors. To overcome these drawbacks, the regression trunk model has been proposed: a multiple regression model with main effects and a parsimonious amount of higher order interaction effects. The interaction effects can be represented by a small tree: a regression trunk. This article proposes a new algorithm—Simultaneous Threshold Interaction Modeling Algorithm (STIMA)—to estimate a regression trunk model that is more general and more efficient than the initial one (RTA) and is implemented in the R-package stima. Results from a simulation study show that the performance of STIMA is satisfactory for sample sizes of 200 or higher. For sample sizes of 300 or higher, the 0.50 SE rule is the best pruning rule for a regression trunk in terms of power and Type I error. For sample sizes of 200, the 0.80 SE rule is recommended. Results from a comparative study of eight regression methods applied to ten benchmark datasets suggest that STIMA and GUIDE are the best performers in terms of cross-validated prediction error. STIMA appeared to be the best method for datasets containing many categorical variables. The characteristics of a regression trunk model are illustrated using the Boston house price dataset.

Supplemental materials for this article, including the R-package stima, are available online.     

Transformation-based model averaged tail area inference

In parameter estimation, it is not a good choice to select a “best model” by some criterion when there is model uncertainty. Model averaging is commonly used under this circumstance. In this paper, transformation-based model averaged tail area is proposed to construct confidence interval, which is an extension of model averaged tail area method in the literature. The transformation-based model averaged tail area method can be used for general parametric models and even non-parametric models. Also, it asymptotically has a simple formula when a certain transformation function is applied. Simulation studies are carried out to examine the performance of our method and compare with existing methods. A real data set is also analyzed to illustrate the methods.     

锥优化模型在Robust桁架拓扑设计实例中的应用

本文讨论Robust桁架拓扑设计(TTD)问题，即桁架结构设计问题，使其在固定重量的情况下，具有最佳的承载能力．本文陈述了几种应用锥优化解Robust TTD问题的方法，并简介了锥优化最新的领域．同时，本文给出了一个单负荷的线性模型和一个多负荷的半正定优化模型以及Robust TTD问题．文中所有的模型均有例证．例证显示通过应用对偶性这些模型的规模能被充分的减小．     

The admissible parameter space for exponential smoothing models

We discuss the admissible parameter space for some state space models, including the models that underly exponential smoothing methods. We find that the usual parameter restrictions (requiring all smoothing parameters to lie between 0 and 1) do not always lead to stable models. We also find that all seasonal exponential smoothing methods are unstable as the underlying state space models are neither reachable nor observable. This instability does not affect the forecasts, but does corrupt the state estimates. The problem can be overcome with a simple normalizing procedure. Finally we show that the admissible parameter space of a seasonal exponential smoothing model is much larger than that for a basic structural model, leading to better forecasts from the exponential smoothing model when there is a rapidly changing seasonal pattern.     

Efficiency Bounds for Product Designs in Linear Models

We provide lower efficiency bounds for the best product design for an additive multifactor linear model. The A-optimality criterion is used to demonstrate that out bounds are better than the conventional bounds. Applications to other criteria, such as IMSE (integrated mean squared error) criterion are also indicated. In all the cases, the best product design appears to perform better when there are more levels in each factor but decreases when more factors are included. Explicit efficiency formulas for non-additive models are also constructed.     

A model to enhance the reliability of the serial parallel systems with component mixing

System reliability, especially for serial parallel systems, has attracted much attention in recent years. Redundancy allocation is a technique to increase the reliability of the serial parallel systems. Supplying redundant components depends on some restrictions such as available budget, weight, space, etc. This paper proposes a new model for redundancy allocation problems (RAPs) by considering discount policy. The proposed model attempts to maximize the reliability of a system by gathering various components where there are some limitations on budgeting. We present two models with different assumptions including all unit discount and incremental discount strategies. The resulted formulations are nonlinear integer models and categorized as NP-hard. Therefore, some heuristics and meta-heuristics are designed to solve the resulted models, efficiently.     

Analytical models for supplier selection and order quantity allocation

In the literature, decision models and techniques for supplier selection do not often consider inventory management of the items being purchased as part of the analysis. In this article, two mixed integer nonlinear programming models are proposed to select the best set of suppliers and determine the proper allocation of order quantities while minimizing the annual ordering, inventory holding, and purchasing costs under suppliers’ capacity and quality constraints. The first model allows independent order quantities for each supplier while the second model restricts all order quantities to be of equal size, as it would be required in a multi-stage (supply chain) inventory model. Illustrative examples are used to highlight the advantages of the proposed models over a previous model introduced in the literature.     

Lead with closed-loop system compensation of a radically rotating elastic rod attached to a rigid body part II: Nonlinear system simulation and control

As was stated in Part I, the linear control models of a radically rotating elastic rod in all the analysis and design procedures for lead with closed-loop system compensation is presented. For a given linear system model, if the model is accurate, it will be accurate only over a very limit range of operation of the system. However, all the effort of design comes to be meaningful until it is tested using the nonlinear system model. On the other hand, the response of the nonlinear system model will not be as good as that of the linear model. In fact, some iterations on the design and on improving the design based-model are often needed before there is even a resemblance between the linear model response and the nonlinear system response. The present paper is a continuation of [1] and nonlinear control system simulation and a tuning process are presented. While almost all design procedures for physical system contain some tuning process, the development of an analytic design procedure for models of distributed-parameter control system can be evidently shown through this paper.     

The Theory of Finite Models without Equal Sign

In this paper, it is the first time ever to suggest that we study the model theory of all finite structures and to put the equal sign in the same situtation as the other relations. Using formulas of infinite lengths we obtain new theorems for the preservation of model extensions, submodels, model homomorphisms and inverse homomorphisms. These kinds of theorems were discussed in Chang and Keisler＇s Model Theory, systematically for general models, but Gurevich obtained some different theorems in this direction for finite models. In our paper the old theorems manage to survive in the finite model theory. There are some differences between into homomorphisms and onto homomorphisms in preservation theorems too. We also study reduced models and minimum models. The characterization sentence of a model is given, which derives a general result for any theory T to be equivalent to a set of existential-universal sentences. Some results about completeness and model completeness are also given.     

Assessing the predictive effectiveness of the variety seeking and reinforcement models

Prediction of customer choice behaviour has been a big challenge for marketing researchers. They have adopted various models to represent customers purchase patterns. Some researchers considered simple zero–order models. Others proposed higher–order models to represent explicitly customers tendency to seek [variety] or [reinforcement] as they make repetitive choices. Nevertheless, the question [Which model has the highest probability of representing some future data?] still prevails. The objective of this paper is to address this question. We assess the predictive effectiveness of the well–known customer choice models. In particular, we compare the predictive ability of the [dynamic attribute satiation] (DAS) model due to McAlister (Journal of Consumer Research, 91, pp. 141–150, 1982) with that of the well–known stochastic variety seeking and reinforcement behaviour models. We found that the stochastic [beta binomial] model has the best predictive effectiveness on both simulated and real purchase data. Using simulations, we also assessed the effectiveness of the stochastic models in representing various complex choice processes generated by the DAS. The beta binomial model mimicked the DAS processes the best. In this research we also propose, for the first time, a stochastic choice rule for the DAS model.