Alternative Decision Rules Research Articles

Statistical decision theory respecting stochastic dominance

The statistical decision theory pioneered by (Wald, Statistical decision functions, Wiley, 1950) has used state-dependent mean loss (risk) to measure the performance of statistical decision functions across potential samples. We think it evident that evaluation of performance should respect stochastic dominance, but we do not see a compelling reason to focus exclusively on mean loss. We think it instructive to also measure performance by other functionals that respect stochastic dominance, such as quantiles of the distribution of loss. This paper develops general principles and illustrative applications for statistical decision theory respecting stochastic dominance. We modify the Wald definition of admissibility to an analogous concept of stochastic dominance (SD) admissibility, which uses stochastic dominance rather than mean sampling performance to compare alternative decision rules. We study SD admissibility in two relatively simple classes of decision problems that arise in treatment choice. We reevaluate the relationship between the MLE, James–Stein, and James–Stein positive part estimators from the perspective of SD admissibility. We consider alternative criteria for choice among SD-admissible rules. We juxtapose traditional criteria based on risk, regret, or Bayes risk with analogous ones based on quantiles of state-dependent sampling distributions or the Bayes distribution of loss.

The promise of potential: A study on the effectiveness of jury selection to a prestigious visual arts program

AbstractWe analyze 11 years of admission decisions to a highly selective post‐graduate visual arts program. Our unique, longitudinal data includes detailed information about the selection procedures as well as the later artistic and economic achievements for both accepted and rejected applicants (n = 8,557). Regarding the predictive value of the selection procedures on later performance, our analyses show that the largest gain made is in the first, more cursory, pre‐selection round. We find that weeding out less promising applicants is easier than identifying later top‐performers, in terms of ex‐ante expectations. The subsequent or final selection round is resource intensive and consists of several interviews with multiple jury members. Here we uncover an implicit structure of criterion variables that helps explain the ex‐post admission decisions. Our simulations show that actual selection during the final round is slightly better than alternative decision rules (including a decision by lottery) in identifying applicants' potential. Nevertheless, measured by future performance, the gain from rigorous jury assessments relative to modest and cheaper selection methods is minimal. Our conclusions are maintained under several robustness checks.

Multimodal EEG and Eye Tracking Feature Fusion Approaches for Attention Classification in Hybrid BCIs

Often, various modalities capture distinct aspects of particular mental states or activities. While machine learning algorithms can reliably predict numerous aspects of human cognition and behavior using a single modality, they can benefit from the combination of multiple modalities. This is why hybrid BCIs are gaining popularity. However, it is not always straightforward to combine features from a multimodal dataset. Along with the method for generating the features, one must decide when the modalities should be combined during the classification process. We compare unimodal EEG and eye tracking classification of internally and externally directed attention to multimodal approaches for early, middle, and late fusion in this study. On a binary dataset with a chance level of 0.5, late fusion of the data achieves the highest classification accuracy of 0.609–0.675 (95%-confidence interval). In general, the results indicate that for these modalities, middle or late fusion approaches are better suited than early fusion approaches. Additional validation of the observed trend will require the use of additional datasets, alternative feature generation mechanisms, decision rules, and neural network designs. We conclude with a set of premises that need to be considered when deciding on a multimodal attentional state classification approach.

Utility maximization versus regret minimization in health choice behavior: Evidence from four datasets.

Choice models in health are almost exclusively based on the neoclassical economic paradigm of utility maximization. Recently developed choice models have captured and shown empirical support for regret minimization as an alternative decision rule. In health economics, recent applications of RRM models indicate that individuals making health-based choices may exhibit regret minimization-type behavior. In this paper, we build on this research using a more flexible model that allows for heterogeneous decision rules, separately from preference heterogeneity, and comparing it to models that assume single decision rules. We use four datasets from diverse settings in which individuals make health choices: tobacco markets, genomic testing, and HIV prevention. We found that, if a one-size-fits-all rule is applied, then utility maximization was preferable to regret minimization for these datasets. However, we also find that individuals apply varying decision rules in similar proportions in these health settings, suggesting that models for heterogeneous decision rules were needed to capture these behaviors in these settings.

Spatial Management to Reduce Entanglement Risk to North Atlantic Right Whales in Fishing Gear: A Case Study of U.S. Northeast Lobster Fishery 2002–2009

Despite the use of gear requirements and access restrictions to manage lobster fishery interactions with north Atlantic right whales since 1997, the population is likely below 370 animals. The Dynamic Area Management (DAM) program (2002–2009) used “real-time” right whale sightings data to provide temporary protection using closures or whale-modified-gear to reduce entanglement. Our ex-post evaluation uses a flexible framework to identify strengths and weaknesses of the program. Biological and economic implications of the program are evaluated using a relative risk of entanglement index (RREI) calculated with spatially and temporally explicit data on density of right whales and fishing effort. An illustrative closure optimization model demonstrates the trade-offs between the non-monetary benefits of risk reduction and the opportunity cost of closures under alternative decision rules (benefit-ranking and cost-effectiveness). Annual aerial sampling to detect DAM areas was low (<3%), yet in some months’ the 17% of area covered by all northeast right whale management areas encompassed up to 70% of the region’s population. Despite their small spatial footprint, dynamic and static measures may have reduced total risk by 6.5% on average, and DAM zones may have created an indirect economic incentive for some fishers to adopt the whale-modified-gear. Similar RREI index values in some months with inverse levels of fishing effort and whale presence highlight the need to consider fishing and whales jointly to reduce risk. These temporal-spatial patterns are critical in policy instrument design. Further, optimization results illustrate how different decision rules can attain equivalent non-monetary benefits of risk reduction at different opportunity costs to industry; the implications of whale-modified-gear and compliance factors are explored. We recommend that DAMs be considered as part of a suite of policy instruments, and highlight how recent technological advances may support lower cost data collection and faster implementation given limited public sector budgets. This case study highlights the need for evaluation of past policy instruments with a lens beyond biological outcomes, and sets the stage for further empirical analysis to better understand harvester responses to management measures designed to protect right whales and the resulting private and public sector trade-offs.

Weighting or aggregating? Investigating information processing in multi-attribute choices.

Multi-attribute choices are commonly analyzed in economics to value goods and services. Analysis assumes individuals consider all attributes, making trade-offs between them. Such decision-making is cognitively demanding, often triggering alternative decision rules. We develop a new model where individuals aggregate multi-attribute information into meta-attributes. Applying our model to a choice experiment (CE) dataset, accounting for attribute aggregation (AA) improves model fit. The probability of adopting AA is greater for: homogenous attribute information; participants who had shorter response time and failed the dominance test; and for later located choices. Accounting for AA has implications for welfare estimates. Our results underline the importance of accounting for information processing rules when modelling multi-attribute choices.

Social tariffs and democratic choice-Do population-based health state values reflect the will of the people?

In economic evaluations of health technologies, health outcomes are commonly measured in terms of quality-adjusted life years (QALYs). QALYs are the product of time and health-related quality of life. Health-related quality of life, in turn, is determined by a social tariff, which is supposed to reflect the public's preference over health states. This study argues that, because of the tariff's role in the societal decision-making process, it should not be understood as merely an operational (statistical) definition of health, but as a major instrument of democratic participation. I outline what implications this might have for both the method used to aggregate individual preferences, and the set of individuals whose preferences should count. Alternative tariff specifications and decision rules are explored, and future research directions are proposed.

Resolving the trade-off between silver eel escapement and hydropower generation with simple decision rules for turbine shutdown

Hydropower plants are commonly reported as a major cause of the worldwide decline of freshwater eels (Anguillidae), so that management solutions are urgently needed to mitigate their impacts. Where downstream passage solutions are complex to develop, turbine shutdown appears as an effective management solution to protect silver eels during their river migration toward spawning areas. However, the definition of operational decision rules for turbine shutdown is challenging due to the duality between the benefit for eel conservation and the concomitant cost in term of hydropower production. Here, we proposed a decision framework for turbine shutdown based on simple hydrological criteria to guide negotiations between stakeholders toward a trade-off between silver eel escapement and hydropower generation. Eel migration was assumed to be triggered by a minimum river flow associated with a minimum discharge pulse, so that threshold values can be directly implemented as decision rules for turbine shutdown. To estimate relevant thresholds, a generic methodological framework was developed to generate alternative decision rules from data collected at hydropower plants, which can include telemetry surveys and estimates of eel abundance. A multiple-criteria decision analysis was then conducted to rank alternatives and to determine the best compromise between promoting silver eel escapement and limiting turbine shutdown duration. Graphic outputs can help stakeholders to understand the competitive interests between eel conservation and hydropower production, while visually identifying a range of consensual alternatives to support negotiations in the choice of operational thresholds. The method was illustrated for three river systems in Europe featured by distinct hydrological conditions and can be applied in other areas, providing that eel monitoring surveys and flow data are available.

Development of a computational modeling laboratory for examining tobacco control policies: Tobacco Town.

A key focus of recent policy efforts to curb tobacco product usage has been the role of place-specifically the density of retail and advertising and the resulting spatial pattern of access and exposure for consumers. Policies can alter the environment by reducing density or shifting distribution of tobacco retail and thus limiting access and exposure. Since little empirical evidence exists for the potential impact of these policies across potentially heterogeneous places, we develop and apply an original spatial computational model to simulate place-based retail tobacco control policies. The model is well-grounded in theory and available empirical evidence. We apply the model in four representative settings to demonstrate the utility of this approach as a policy laboratory, to develop general insights on the relationship between retailer density, retail interventions, and tobacco costs incurred by consumers, and to provide a framework to guide future modeling and empirical studies. Our results suggest that the potential impact on costs of reducing tobacco retailer density are highly dependent on context. Projected impacts are also influenced by assumptions made about agent (smoker) purchasing decision-making processes. In the absence of evidence in this area, we tested and compared three alternative decision rules; these interact with environmental properties to produce different results. Agent properties, namely income and cigarettes per day, also shape purchasing patterns before and after policy interventions. We conclude that agent-based modeling in general, and Tobacco Town specifically, hold much potential as a platform for testing and comparing the impact of various retail-based tobacco policies across different communities. Initial modeling efforts uncover important gaps in both data and theory and can provide guidance for new empirical studies in tobacco control.

Economic Benefits of Derivatives for Long Term Investments-Equity Linked Securities

In this paper, we examined the economic benefits of derivatives in the aspect of investment assets. Our study differs from previous studies in that it analyzed the differences in the economic benefits of derivatives between for short term investors and for long term investors, and focused on the equity linked securities (ELS) rather than plain vanilla derivatives. We found the following results from the analysis over 1 to 20 years of investment horizons for four different types of equity linked securities, including ‘Auto-callable ELS’, ‘Knock-out ELS’, ‘Digital ELS’ and ‘Reverse Convertible ELS.’ First, equity linked securities contribute to improving the performance of the optimal portfolio for most investors, except for some investors who have extremely low degrees of risk aversion. Second, these economic benefits of equity linked securities are consistently observed regardless of investment horizon. Third, investment demand for equity linked securities is higher for investors with a medium-level of risk aversion rather than for aggressive or conservative investors. In addition, equity linked securities are mainly used as substitutes for risk-free bonds rather than risky assets (i.e., stocks). Finally, most of our results are still valid even when different market environments are assumed or alternative decision rules are used to derive investors’ optimal portfolio.

Does exposure to alternative decision rules change gaze patterns and behavioral strategies in games?

We run an eye-tracking experiment to investigate whether players change their gaze patterns and choices after they experience alternative models of choice in one-shot games. In phase 1 and 3, participants play 2 × 2 matrix games with a human counterpart; in phase 2, they apply specific decision rules while playing with a computer with known behavior. We classify participants in types based on their gaze patterns in phase 1 and explore attentional shifts in phase 3, after players were exposed to the alternative decision rules. Results show that less sophisticated players, who focus mainly on their own payoffs, change their gaze patterns towards the evaluation of others’ incentives in phase 3. This attentional shift predicts an increase in equilibrium responses in relevant classes of games. Conversely, cooperative players do not change their visual analysis. Our results shed new light on theories of bounded rationality and on theories of social preferences.

Logistic regression, neural networks and Dempster–Shafer theory: A new perspective

We revisit logistic regression and its nonlinear extensions, including multilayer feedforward neural networks, by showing that these classifiers can be viewed as converting input or higher-level features into Dempster–Shafer mass functions and aggregating them by Dempster’s rule of combination. The probabilistic outputs of these classifiers are the normalized plausibilities corresponding to the underlying combined mass function. This mass function is more informative than the output probability distribution. In particular, it makes it possible to distinguish between lack of evidence (when none of the features provides discriminant information) from conflicting evidence (when different features support different classes). This expressivity of mass functions allows us to gain insight into the role played by each input feature in logistic regression, and to interpret hidden unit outputs in multilayer neural networks. It also makes it possible to use alternative decision rules, such as interval dominance, which select a set of classes when the available evidence does not unambiguously point to a single class, thus trading reduced error rate for higher imprecision.

Green supply chain analysis under cost sharing contract with uncertain information based on confidence level

In this paper, we study supply chain coordination issues arising out of green supply chain consisting of a manufacturer and a retailer under cost sharing contract with uncertain information. Instead of expected utility maximization, we present an alternative decision rule based on confidence level, that is, both the manufacturer’s and the retailer’s aims are to maximize the potential incomes under their confidence levels. First, we obtain the equilibrium values for the decentralized and the centralized channel cases under the given confidence levels, then compare the equilibrium values between the decentralized channel case and the centralized channel case to motivate cost sharing contract framework. Second, we consider the retailer participates in the green channel and obtain that the manufacturer and the retailer incur higher profits in the cost sharing contract case than the decentralized supply chain case. Third, we propose a cost sharing contract between the players who bargain on the cost sharing parameter, and the contract benefits the manufacturer significantly through sharing of costs with the retailer.

Investigating Behavioral Differences in Heterogeneous Decision Rule Segments: An Empirical Analysis

Conventional and contemporary models of travel choice make the restrictive assumption of homogeneity in decision rules. Recent literature has shown empirical evidence for potential heterogeneity in decision rules with regard to utility maximization and regret minimization. Notwithstanding these advances in modeling decision rules, behavioral understanding in the differences in these alternative decision rule segments has not been sufficiently understood. Moreover, the factors which influence the choice of these decision rules have not received significant attention. This study proposes a framework which considers decision makers to have both utility maximizing and regret minimizing tendencies. The variation in these tendencies across decision makers renders the framework heterogeneous. A heterogeneous decision rule model is developed assuming the decision rule adopted to be a latent construct. The study characterizes the regret minimizing and utility maximizing segments based on average values of the segmental attributes. The empirical findings show evidence to confirm that utility maximizers tend to be predominantly captive to personal vehicle usage while regret minimizers might be non-captive to any particular mode. The nature and extent of influence of factors affecting the choice of decision rule is also examined.

Optimization of decision rules for hydroelectric operation to reduce both eel mortality and unnecessary turbine shutdown: A search for a win–win solution

AbstractWorldwide populations of freshwater eels have declined with one of the contributing causes related to mortality during passage through hydropower turbines. An inherent trade‐off underlies turbine management where the competing demand for more hydropower comes at the expense of eel survival. A win–win solution exists when an option performs better on all competing demands compared to other options. A predictive model for eel migration based on a recent telemetry study was used to develop decision rules for turbine management in the Shenandoah River system. The performance of alternative decision rules was compared to the status quo policy to search for win–win solutions. Decision rules were defined by the probability of eel movement and were evaluated by the probabilities of false positive and false negative errors. The exact value of the cut‐off probability used in the decision rule will need to be determined through negotiation between stakeholders, but a range of cut‐off probabilities resulted in a win–win situation with both reduced eel mortality and increased turbine operation relative to the current shutdown strategy. Monitoring the implementation is needed to evaluate and update the predictive model and to refine the decision rule. Although the decision is framed for the Shenandoah River system, the analytical approach could be used to develop decision rules for turbine shutdown policy in other areas.

Analysis of the modified alternative decision rule in the preclustering algorithm

The preclustering algorithm as opposed to other existed algorithms does not require a priori information about cluster location and about additional means of control. Preclustering algorithm is multipurpose and promising for a primary analysis of investigated input data. In this article the main part of the preclustering algorithm – the modified decision rule has been presented. The modification consisted to the replacement of the calculation of mean distances in a precluster (like in the classical decision rule) by the mean distances from the center of the precluster to all objects in the chosen precluster. The proposed decision rule determines the centre of the group as a local density maximum of the group of objects (before clustering) or of the precluster (after clustering). The results obtained during the testing of the decision rule were compared with the results obtained with the use of criteria of spherical resolution. Also, from the analysis, the advantages and disadvantages of the proposed decision rule have been identified.

Heuristics-in-use in industrial interfirm-collaborating clusters

Purpose – The purpose of this paper is to help interfirm-collaborating cluster (ICC) executives examine the relevance of alternative decision rules in practical business contexts. Multi-party-implemented strategies and establishing multi-lateral collaborations are necessary actions for achieving success in new product development by small and medium enterprises (SMEs). This study explores interfirm decision-making heuristics relating to industrial ICCs. Design/methodology/approach – The study examines the relevancy to decision making in ICCs of heurstics such as “fast-and-frugal decision trees” (FFDTs) and “take-the-best” (TTB) to processing possibly influential decision-making cues. The study also examines simple heuristics versus the value of a “fully rational” approach to making decisions – calculating cue values, importance weights, multiplying values by weights, summing and selecting the option having the highest summed score. This study included interviewing executives of the pivotal firm in an ICC. Findings – This study reveals a decision-making solution for shortening the time and processes required in seeking new business collaboration partners in an ICC. This study not only develops a FFDT for six decision-making modules to quickly identify potential collaboration partners, but it also constructs a decision systems analysis (DSA) flowchart to effectively shorten the decision-making process. Research limitations/implications – This study is in accordance with the general type of industrial interfirm collaboration in Taiwan. The industrial interfirm collaboration could be further divided into the types of formal, semi-formal and informal industrial interfirm collaborations. Practical implications – This study argues that firms usually find it difficult to develop their own technology because of the high costs of research and development for SMEs. Therefore, firms need to collaborate with partners to maintain their competitive advantage. However, to collaborate, firms must learn to trust their collaboration partners, and the degree of collaboration also strongly depends on the degree to which they trust their collaboration partners. Originality/value – This study provides the efficient models of FFDT and DSA to quickly identify potential collaboration partners and to effectively shorten decision-making processes.

Reassessing Proximity Voting: Expertise, Party, and Choice in Congressional Elections

Spatial theories of voting are appealing because they link voters’ electoral choices to candidates’ policy positions. Yet if voters lack political sophistication and awareness of candidate positions, they may not measure up to the cognitive demands of spatial voting models. Using district experts to ascertain House candidates’ positions on the same liberal-conservative scale as in a survey of constituents, we find that proximity voting is common, even among voters unaware of candidates’ ideological positions. Since voting based on party identification or presidential approval often produces votes consistent with the spatial model, such alternative decision rules explain this result by serving as powerful proxies for proximity voting. In addition, facilitator variables such as involvement in politically expert interpersonal networks, the ideological difference between candidates, and voters’ distance from the district ideological cut point help explain proximity voting.

Impact of Different Dimensions of Corporate Social Responsibility on Tourism Demand: Does the Status Quo Matter?

The authors, using discrete choice experiments, study the economic valuation of corporate social responsibility (CSR) policy measures in sun-and-beach tourist destination demand. They also examine the role of the status quo effect on CSR actions in tourist destinations. The status quo effect occurs because people generally place much more value on avoiding a loss than on acquiring a gain. Visitors to Cartagena de Indias (Colombia) were presented with alternative profiles of CSR measures and were given one of two treatments that varied according to the definition of the status quo alternative and the valuation question. The design of the experiments enabled the authors to compare the respondents' willingness to pay (WTP) a higher price for their holiday in a destination that has in place several CSR measures and willingness to accept (WTA) a lower price for the same destination with a lower CSR profile. The data are modelled using a flexible approach that allows for the consideration of alternative decision rules in the visitor's decision process. The results show that tourists care about CSR attributes and are likely to make their vacation choices on the basis of such attributes. Moreover, in this context the standard economic theory assumption of preferences symmetry is not satisfied. In other words, the cost of not implementing CSR actions is higher than the benefits of implementing them. When a destination increases CSR actions the number of visitors and their WTP for their visit are likely to increase, but at substantially lower rates than the WTP for alternative destinations (WTA) when the destination reduces its CSR actions. These results may explain why conventional studies find ambiguous effects of CSR action on tourist choice.

A simple clinical decision rule to rule out appendicitis in patients with nondiagnostic ultrasound results.

The objective was to identify a set of clinical features that can rule out appendicitis in patients with suspected acute appendicitis and nondiagnostic ultrasound (US) results, allowing safe discharge and next-day reevaluation without initial computed tomography (CT) or magnetic resonance imaging (MRI). Data on clinical and US evaluation, including a number of prespecified variables potentially associated with acute appendicitis, were prospectively collected in two diagnostic accuracy studies of imaging. These studies included patients with suspected appendicitis seen in the emergency department (ED). For development and validation of the clinical decision rule (CDR), only patients with inconclusive or negative US results were included. There were 199 (of 422) patients in the development cohorts and 120 (of 211) patients in the validation cohort. Logistic regression analysis was used for data from patients with inconclusive or negative US results, and profiles were created of all possible combinations of predictors retained in the multivariable model. A final diagnosis was assigned by an expert panel based on perioperative data, histopathology, and clinical follow-up of at least 3 months. The CDR selected patients after negative or inconclusive US for discharge and next-day reevaluation without initial CT or MRI if fewer than two of the following predictors were present: male sex, migration of pain to the right lower quadrant, vomiting, and white blood cell (WBC) count higher than 12.0 × 10(9) /L. Applying the CDR in the development set selected 126 of 199 (63%) patients with negative or inconclusive US results for discharge without further imaging. This rule reduced the probability of appendicitis from 26% (51 of 199) in the total group of patients with negative or inconclusive US results to 12% (15 of 126) in the group that would be discharged based on the rule (p = 0.001). In the validation set (n = 120), the decision rule selected 72 (60%) patients for discharge and next-day reevaluation and reduced the probability of appendicitis from 20% (24 of 120) in the total group to 6% (4 of 72) in the patients selected on the rule (p = 0.001). The negative predictive value of the decision rule in the validation set was 94% (95% confidence interval [CI] = 87% to 98%). In comparison, the negative predictive value of CT in the same group was 99% (95% CI = 93% to 100%, p = 0.14), and that of MRI was 99% (95% CI = 94% to 100%, p = 0.12). Alternative decision rules based on combinations of the present decision rule with C-reactive protein (CRP) results did not improve selection. This newly developed CDR significantly reduces the probability of appendicitis in a large subgroup of patients with negative or inconclusive US results. These patients can be safely discharged for outpatient reevaluation without further initial imaging if proper follow-up is available. This could assist in lowering the number of ED imaging investigations in patients with suspected appendicitis.