Ambiguous Criteria Weights in AHP: Consequences and Solutions*

Two related streams of criticism of the analytic hierarchy process (AHP) have not yet been satisfactorily resolved, although both date from the early 1980s. The first relates to ambiguity in the meaning of the relative importance of one criterion as compared to another. The second is concerned with reversals of rank alleged to be possible when new options are introduced in an AHP problem. Both proponents and critics of AHP agree that rank reversals occur, but disagree on the legitimacy of such reversals. This paper shows that there is a necessary correspondence between the manner in which criteria importances are interpreted and computed and the manner in which the weights of the options under each criterion are normalized. In general, if this relationship is ignored, incorrect weights are generated for options under consideration regardless of whether new options are added or deleted. A rank reversal on the addition of an option is merely symptomatic of this fact, and such reversals do not occur when the correspondence condition is met.     

Inference in a Binary Response Model with Applications to Data Analysis*

Standard errors of the coefficients of a logistic regression (a binary response model) based on the asymptotic formula are compared to those obtained from the bootstrap through Monte Carlo simulations. The computer intensive bootstrap method, a nonparametric alternative to the asymptotic estimate, overestimates the true value of the standard errors while the asymptotic formula underestimates it. However, for small samples the bootstrap estimates are substantially closer to the true value than their counterpart derived from the asymptotic formula. The methodology is discussed using two illustrative data sets. The first example deals with a logistic model explaining the log-odds of passing the ERA amendment by the 1982 deadline as a function of percent of women legislators and the percent vote for Reagan. In the second example, the probability that an ingot is ready to roll is modelled using heating time and soaking time as explanatory variables. The results agree with those obtained from the simulations. The value of the study to better decision making through accurate statistical inference is discussed.     

Data Driven Modeling: An Application in Scheduling

This paper presents a data driven modeling (DDM) approach to certain types of optimization problems. DDM relinquishes control of the completed model to the user department rather than the operations research (OR) staff. The approach emphasizes development of models that are dependent on data maintained and understood by the users. The data base consists of coded user rules which describe when changes will occur in the problem structure and data which captures the generalization of the problem. Both the rules and data can be updated by user department personnel. These data drive a matrix generator controlled by the rules which uses the data base as input to generate the specific model formulation. This DDM system is designed by OR consultants or staff to allow independence of use along with low-cost and minimal-effort maintenance. The DDM approach is illustrated with an application to a real-world medical scheduling problem.     

USING CONJOINT ANALYSIS TO PREDICT TRIAL AND REPEAT-PURCHASE PATTERNS OF NEW FREQUENTLY PURCHASED PRODUCTS*

A new approach is proposed to evaluate new-product opportunities. This approach uses the distribution of brand-purchase probability of the new product over a population of potential customers and the outputs from conjoint analysis. The heterogeneous distribution of brand-purchase probability is expressed by a beta binomial brand-choice model compounded with a negative binomial product-class purchase-incidence model. The resulting model provides a way to predict trial and repeat-purchase patterns of new-product concepts. The paper discusses the development of the model. It also discusses issues of measurement, estimation, testing, and implementation of the proposed approach based on actual empirical data.     

Sustainable supply chain management and the transition towards a circular economy: Evidence and some applications

In the last decades, green and sustainable supply chain management practices have been developed, trying to integrate environmental concerns into organisations by reducing unintended negative consequences on the environment of production and consumption processes. In parallel to this, the circular economy discourse has been propagated in the industrial ecology literature and practice. Circular economy pushes the frontiers of environmental sustainability by emphasising the idea of transforming products in such a way that there are workable relationships between ecological systems and economic growth. Therefore, circular economy is not just concerned with the reduction of the use of the environment as a sink for residuals but rather with the creation of self-sustaining production systems in which materials are used over and over again.Through two case studies from different process industries (chemical and food), this paper compares the performances of traditional and circular production systems across a range of indicators. Direct, indirect and total lifecycle emissions, waste recovered, virgin resources use, as well as carbon maps (which provide a holistic visibility of the entire supply chain) are presented. The paper asserts that an integration of circular economy principles within sustainable supply chain management can provide clear advantages from an environmental point view. Emerging supply chain management challenges and market dynamics are also highlighted and discussed.     

Constructing a strategy map for banking institutions with key performance indicators of the balanced scorecard

This study presents a structural evaluation methodology to link key performance indicators (KPIs) into a strategy map of the balanced scorecard (BSC) for banking institutions. Corresponding with the four BSC perspectives (finance, customer, internal business process, and learning and growth), the most important evaluation indicators of banking performance are synthesized from the relevant literature and screened by a committee of experts. The Decision Making Trial and Evaluation Laboratory (DEMATEL) method, a multiple criteria analysis tool, is then employed to determine the causal relationships between the KPIs, to identify the critical central and influential factors, and to establish a visualized strategy map with logical links to improve banking performance. An empirical application is provided as an example. According to the expert evaluations, the three most essential KPIs for banking performance are customer satisfaction, sales performance, and customer retention rate. The DEMATEL results demonstrate a clear road map to assist management in prioritizing the performance indicators and in focusing attention on the strategy-related activities of the crucial indicators. According to the constructed strategy map, management could better invest limited resources in the areas that need improvement most. Although these strategy maps of the BSC are not universal, the research results show that the presented approach is an objective and feasible way to construct strategy maps more justifiably. The proposed framework can be applicable to institutions in other industries as well.     

USING AN UNCERTAINTY MODEL TO ASSESS SALES RESPONSE TO ADVERTISING*

Implications of a probabilistic “random walk” model of incremental sales response to advertising are developed for various timing patterns of advertising expenditures. Maximum likelihood procedures for assessing advertising effectiveness and for estimating a decay (forgetting) rate are developed and applied to artificial data of known configuration and are used to assess the impact over time of a brochure program on mail-order sales. Results are also compared to those from alternative models involving various lag patterns in advertising effects.     

A KNOWLEDGE-BASED DSS FOR MANAGERIAL PROBLEM DIAGNOSIS

A knowledge-based system supporting managerial problem diagnosis is described. The system provides the capability to monitor values of selected variables for problem situations. When problems are located, a list of problem symptoms is delivered to a problem processor for structuring and diagnosis. Problem structuring is based on a combination of concepts from expert systems and structural modeling. User assertions about cause-effect relationships between pairs of variables are maintained in a semantic network. Problem diagnosis uses the relationships in the semantic network to construct causation trees, the branches of which represent potential explanations of the problem symptoms. Mathematical models are constructed based on causation-tree branches, and values from the data base are used to test whether the model confirms the diagnosis. If so, the source of the problem has been located and it is then up to the user to resolve the problem. If the model fails to explain the problem, the model apparently is deficient and the user may perform “what if…” type scenarios in attempts to improve the model and search for problem causes. Realistic applications in the accounting and health care areas are discussed.     

Applications and Implementation DECISION SUPPORT SYSTEMS: AN EMPIRICAL ASSESSMENT FOR DECISION MAKING

A laboratory experiment examined the effects of applying decision support system (DSS) technology to decision making in ill-structured problem environments under varying information conditions. Marketing executives participated in the experiment which investigated the effects of DSS availability, DSS training, and data availability on dependent variables that included: (1) the number of alternatives considered by a subject during decision making, (2) the period of time spent by a subject to complete the decision-making process, (3) the subject's perceived confidence in the decisions he or she had made, (4) the amount of data considered by a subject's during decision making, (5) the individual subject's decision processing, and (6) the subject's performance overall. Our results indicate that all three factors significantly affect the number of alternatives considered by subjects during the decision-making process. We therefore suggest that DSS training be coordinated with decision training in order to realize the potential of DSSs as described in the DSS literature.