Choice Set Research Articles

The performance of full versus partial profile choice set designs in environmental valuation

An issue constantly raising concerns is the complexity of choice sets in stated choice experiments. Generally, designing choice sets requires trade-offs between the amount of information the researcher can derive, primarily through the number of attributes, and the measurement error caused by increased complexity. However, leaving specific attributes out might misrepresent the good in question and result in less information for decision-makers. An opportunity to reduce this trade-off is to apply partial profile designs. The basic idea is that not all attributes vary on all choice sets and that the overlap among attribute levels is controlled by the experimental design. Partial profile designs have rarely been used in environmental valuation, and if so, no split-sample approach was used to investigate performance differences. In this study, we aim to fill this gap by utilising both design types to value the good environmental status of the German North and Baltic Sea. We find that the partial profile design leads to significantly lower willingness-to-pay estimates, increased statistical efficiency as well as higher attribute attendance and less random choices. We thus recommend that researchers should consider partial profile designs more often as they promise clear benefits.

A random-utility-consistent machine learning method to estimate agents’ joint activity scheduling choice from a ubiquitous data set

We propose an agent-based mixed-logit model (AMXL) that is estimated with inverse optimization (IO) estimation, an agent-level machine learning method theoretically consistent with a utility-maximizing mixed logit model framework. The method provides joint, individual-specific, and deterministic estimation, which overcomes the limitations of discrete choice models (DCMs) given ubiquitous datasets. A case study of the CBD in Shanghai is conducted with mobile phone data of 26,149 anonymous commuters whose whole-day activity schedule on weekdays contains three sub-choices and 1,470 alternatives. AMXL is built to estimate individual tastes and predict the activity scheduling choice in different scenarios. Multinomial logit model (MNL), mixed logit model (MXL), and their dynamic forms (DMNL, DMXL) are built as benchmarks. Prediction accuracies are calculated as the percentage consistency of observed choices and predicted choices, both at individual level (to each commuter) and aggregated level (to each alternative in the choice set). The results show that empirical coefficient distributions in AMXL are neither Gumbel nor Gaussian, i.e. capturing inter-individual heterogeneities in space that are hard for DCMs to capture. The prediction accuracy of AMXL is significantly higher than the best model (DMXL) in benchmarks, improving from 8.66% to 61.68% at aggregated level and from 1.69% to 4.33% at individual level. In a comparison scenario, AMXL predicts different while reasonable change of choices compared with benchmark models. In an optimization scenario, AMXL can be directly integrated into a binary programming (BP) problem, which optimally allocates 10 blocks to send restaurant coupons to increase population consumer surplus by 19%.

A Note on Binary Strategy-Proof Social Choice Functions

Let Φn be the set of the binary strategy-proof social choice functions referred to a group of n voters who are allowed to declare indifference between the alternatives. We provide a recursive way to obtain the set Φn+1 from the set Φn. Computing the cardinalities |Φn| presents difficulties as the computation of the Dedekind numbers. The latter give the analogous number of social choice functions when only strict preferences are admitted. A comparison is given for the known values. Based on our results, we present a graphical description of the binary strategy-proof social choice functions in the case of three voters.

Estimating an EQ-5D-Y-3L Value Set for China.

The standard EQ-5D-Y-3L valuation protocol applies DCE data as the primary preference source to model the relative importance of dimensions while cTTO data served to anchor the DCE coefficients onto the QALY scale. This study aims to estimate an EQ-5D-Y-3L value set for China following this protocol, but with a larger cTTO design to better understand the role of cTTO data in estimating EQ-5D-Y-3L value sets. In total, 150 choice sets and 28 EQ-5D-Y-3L health states were valued using DCE and cTTO methods with two independent samples, respectively. General public from 14 different regions were recruited using quota sampling method to achieve representativeness. We compared two modelling strategies: (1) fit the DCE data with mixed logit model with correlated coefficients and a subsequent mapping procedure for anchoring; (2) fit the DCE and TTO data jointly in a hybrid model. Two evaluation criteria (1) coefficient significance and monotonicity; (2) prediction accuracy of the observed cTTO values were used to select the value set. In total, 1476 individuals participated in the study, with 1058 participated the DCE interview and 418 participated the cTTO interview. The highest mean TTO value was 0.924 for state 11112 and the lowest mean TTO value was -0.088 for state 33333. The hybrid model with an A3 term performed the best and was selected as the value set. Following the international protocol and using a larger cTTO design, this study established the EQ-5D-Y-3L value set using a hybrid model for China. Future EQ-5D-Y-3L valuation study could consider using a larger cTTO design for estimating the value set.

Developing an Australian utility value set for the Early Childhood Oral Health Impact Scale-4D (ECOHIS-4D) using a discrete choice experiment

PurposePreference-based quality of life measures (PBMs) are used to generate quality-adjusted life years (QALYs) in economic evaluations. A PBM consists of (1) a health state classification system and (2) a utility value set that allows the instrument responses to be converted to QALYs. A new, oral health-specific classification system, the Early Childhood Oral Health Impact Scale-4D (ECOHIS-4D) has recently been developed. The aim of this study was to generate an Australian utility value set for the ECOHIS-4D.MethodsA discrete choice experiment with duration (DCETTO) was used as the preference elicitation technique. An online survey was administered to a representative sample of Australian adults over 18 years. Respondents were given 14 choice tasks (10 tasks from the DCE design of 50 choice sets blocked into five blocks, 2 practice tasks, a repeated and a dominant task). Data were analyzed using the conditional logit model.ResultsA total of 1201 respondents from the Australian general population completed the survey. Of them, 69% (n = 829) perceived their oral health status to be good, very good, or excellent. The estimated coefficients from the conditional logit models were in the expected directions and were statistically significant (p < 0.001). The utility values for health states defined by the ECOHIS-4D ranged from 0.0376 to 1.0000.ConclusionsThis newly developed utility value set will enable the calculation of utility values for economic evaluations of interventions related to oral diseases such as dental caries among young children. This will facilitate more effective resource allocation for oral health services.

Beyond productivity, does the adoption of agricultural technologies improve food consumption and reduce poverty? Empirical evidence from Benin

ABSTRACT Beyond productivity, does the adoption of agricultural technologies improve food consumption and reduce poverty? To provide answers to this, the paper used data from the household survey on the Comprehensive Food Security and Vulnerability Analysis (CFSVA) carried out in 2017 in Benin. Five agricultural technologies were considered in this study. First, an extended ordered probit model was estimated to analyze the impact of technology choice sets on food consumption groups (poor, limit and acceptable). Second, an extended probit model is employed to assess the impact on poverty status. The results show that the adoption of multiple technologies increases food consumption and reduces poverty among agricultural households in Benin. Combinations of technologies that enhance both food consumption and poverty status are irrigation and herbicide, irrigation and chemical fertilizers and improved seed and chemical fertilizers. Therefore, policy interventions should help farming households gain access to these improved technologies to improve food security and reduce poverty.

Exploring the choice between in-store versus online grocery shopping through an application of Semi-Compensatory Independent Availability Logit (SCIAL) model with latent variables

This paper examines individuals' choice of in-store and online grocery shopping channels using stated preference (SP) choice experiments. The study uses 1,391 records from a stated preference choice experiment in the Greater Toronto Area (GTA), Canada. It applies a Semi-Compensatory Independent Availability Logit (SCIAL) Model with latent variables. The methodology accounts for semi-compensatory choice behaviour through probabilistic choice set formation considering effects from socioeconomic and psychological variables. This study demonstrates the advantage of considering probabilistic choice set formation and semi-compensatory behaviour in modelling the adoption of innovative products. Empirical results reveal that shoppers demonstrated similar myopic behaviours once they firmly considered in-store grocery and subscribed free delivery services in their choice sets. They are equally likely to choose both channels without careful comparison to alternative channels once they firmly consider both channels in the choice set. However, considering the latter in choice sets is much costlier than in-store shopping. Therefore, in-store grocery shopping will still dominate the grocery shopping channel unless all home delivery services become free. Moreover, grocery shoppers value same-day delivery service. For typical delivery services charged between $4 and $20 in the GTA, Canada, grocery shoppers are willing to pay between $3.91 and $8.44 for same-day delivery. The latent variable describing shoppers’ perceived pandemic fear significantly contributes to the choice set inclusion probability of in-store grocery pick-up services, but the effect is not significant for other home delivery channels. This highlights heterogeneity in grocery shoppers' choice behaviour within the online channel.

Attitudes toward choice with incomplete preferences: An experimental study

We present an experiment to test different individual attitudes toward choice, such as preference for flexibility, choice aversion, betweenness and choice neutrality. Unlike other related experimental papers, we want to analyze whether different choice attitudes can coexist for the same subject, depending on the characteristics of the choice set she is facing. In particular, our main hypothesis is that the presence of incomparability among the alternatives in the choice set, and the time at which such incomparability is solved, affect crucially the kind of attitude towards choice that the subject will exhibit. We find that, indeed, choice attitudes are not homogeneous across choice sets, yet they are conditional on the preferences over the alternatives. We also find some evidence supporting that subjects tend to value heuristically sets as a whole.

Intergenerational income mobility and economic freedom

AbstractNumerous studies have found that income inequality reduces the chances of upward relative mobility (i.e., climbing up the income ladder). However, most of this work ignores the role played by institutional quality (namely, economic freedom) in determining mobility and increasing the individual's set of choices. We fill this gap by empirically testing the direct and indirect (through economic growth) impacts of economic freedom on intergenerational income mobility. We find that economic freedom has both direct and indirect effects on intergenerational income mobility, while income inequality is a strong predictor of downward income mobility. When we incorporate findings about the purely mechanical relationship between inequality and intergeneration income mobility, we find that the legal system and property rights component of economic freedom matters more than inequality. These results suggest that good institutions can increase intergenerational income mobility.

IS EVERY PATH THE RIGHT PATH? A SEMIOLOGICAL ANALYSIS OF THE AXIOLOGICAL CHOICES IN MR NOBODY (2009)

Jaco Van Dormael’s 2009 film Mr Nobody presents the viewer with a set of different choices and lives. The explicit moral of the film is that each of these lives is the right one, that every path is the right path. This paper proposes a semiotic analysis of the romantic interests of Nemo to investigate whether this is truly the case. Through the use of different semiological models (among others Metzian semiotics of cinema, Fontanille and Zilverberg’s tensive model and Greimas’ semiotic square), it disproves the axiological position of the film and shows that the different lives of Nemo are presented as unequal.

Boosting aerobic microbial protein productivity and quality on brewery wastewater: Impact of anaerobic acidification, high-rate process and biomass age

Consortia of aerobic heterotrophic bacteria (AHB) are appealing as sustainable alternative protein ingredient for aquaculture given their high nutritional qualities, and their production potential on feed-grade industrial wastewater. Today, the impacts of pre-treatment, bioprocess choice and key parameter settings on AHB productivity and nutritional properties are unknown. This study investigated for the first time AHB microbial protein production effects based on (i) raw vs anaerobically fermented brewery wastewater, (ii) high-rate activated sludge (HRAS) without vs with feast-famine conditions, and (iii) three short solid retention time (SRT): 0.25, 0.50 and 1.00 d. High biomass (4.4–8.0 g TSS/L/d) and protein productivities (1.9–3.2 g protein/L/d) were obtained while achieving COD removal efficiencies up to 98 % at SRT 0.50 d. The AHB essential amino acid (EAA) profiles were above rainbow trout requirements, excluding the S-containing EAA, highlighting the AHB biomass replacement potential for unsustainable fishmeal in salmonid diets.

Non‐compromise extreme effect: Attribute discriminability and preference for an extreme alternative

AbstractIn this research, we show that despite a choice set configuration that promotes the compromise effect, consumers do not always prefer the middle alternative but rather choose the extreme option when one of the attributes has higher discriminability than the other. We use findings from the numerical cognition literature to demonstrate why this happens and, more importantly, provide a novel theoretical framework for what we call the “non‐compromise extreme effect.” The findings are unique to the compromise effect literature, which has consistently shown the effect to be robust. More importantly, the findings show that a brand can successfully compete with a well‐established competitor when it performs better on the low performing attribute, which gives a leeway to managers to take share away from the competitor.

An Approximation of Freedom: On-demand Therapy and the Feminization of Labor

Platform labor and gig work have become key sites for understanding a nascent "future of work" hallmarked by informalization and digitization. A growing body of research emphasizes how experiences of platform work are mediated not only by algorithms and user interfaces, but also by gender, race, local cultures as well as labor hierarchies. Drawing from ongoing ethnographic research on the digital transformation of healthcare, we show how therapists' experiences of platform labor are centrally shaped by the historical and ongoing feminization of mental health work. Platforms reinscribe feminized labor conditions that are pervasive in the healthcare industry, and yet platform labor appears as 'useful' to some therapists as they navigate a set of precarious career choices fundamentally structured by feminization. We use the analytic of the stopgap to describe platforms' two-fold reproduction of the status quo: first by offering an approximation of freedom to individual workers, helping to forestall a crisis of unsustainable work conditions; and second by reinscribing the same logics of exploitation in order to make labor scalable. This stopgap analytic reorients the focus away from the impact of the platforms technologies as such, towards the conditions that make stopgap solutions necessary for survival. It also points towards the importance of intervening in the conditions of exclusion and exploitation that help to create a market for platform stopgaps.

Application of choice models in tourism recommender systems

AbstractChoice models (CM) are proposed in the field of tourism recommender systems (TRS) with the aim of providing algorithms with both a theoretical understanding of tourist's motivations and a certain degree of transparency. The goal of this work is to overcome some of the limitations of current state‐of‐art algorithms used in TRSs by providing: (1) accurate preferences, which are learnt from user choices rather than from ratings, and (2) interpretable coefficients, which are achieved by means of the set of estimated parameters of CM. The study was carried out with a gastronomic data set generated in an ecological experiment in the tourism domain. The performance of CM has been compared with a set of baseline algorithms (rating‐based and ensembles) by using two evaluation metrics: precision and DCG. The CM outperformed the baseline algorithms when the size of the choice set was limited. The findings suggest that CM may provide an optimal trade‐off between theoretical soundness, interpretability and performance in the field of TRS.

To touch or not to touch: Examining the role of choice set size

AbstractTouch is a powerful means to explore one's environment and a critical sensory modality for information gathering. Previous research has shown the positive effects of product touch on key outcomes such as perceived product ownership and choice confidence, yet only in the context of consumers examining a solitary product or a small choice set. The current research draws on the choice overload hypothesis to examine whether a large choice set size attenuates the positive effects of touch. Our findings suggest that product touch results in more positive outcomes when choice sets are small (vs. large), with perceived choice difficulty mediating this effect (Experiment 1). The interactive effect of choice set size and touch is diminished in situations where touch conveys limited additional product information (Experiment 2). Further, we find that touching a large choice set can be advantageous among certain consumers, as those with a maximizing mindset respond more favorably to a large choice set when they can touch the items versus not (Experiment 3). We discuss research implications for the literatures on product touch, choice overload, and consumer mindsets, and practical implications for marketers as pertaining to assortment management, message framing, and online retail shopping environments.

Spec guidance for engineering design based on data mining and neural networks

Recently, many studies on product design have been utilizing online data. They analyze user-generated online data and draw design implications. However, most of them provide customers’ tendency for feature categories rather than spec ranges for sub-features, which are crucial in industrial applications. This paper proposes an approach based on data mining and neural networks to extract spec guidance for engineering design from online data. First, product sub-features are extracted from online data, and customer choice sets are constructed. Next, a neural network choice model is trained based on these choice sets. Finally, the model is interpreted by SHAP (SHapley Additive exPlanations). In the final stage, this study proposes a method for analyzing the obtained SHAP values to draw new design implications. The suggested approach was tested on smartphone review data, and the result provides a set of recommended spec values for each sub-feature. The resultant spec guidance can help companies design a product with spec configuration preferred by customers.

The Impact of Price Preciseness, Price Reduction, and Lay Rationalism on Travelers’ Perceptions of Deal Attractiveness, Purchase Intention, and Choice

This research investigated the role of price preciseness (rounded vs. precise) in perceiving deal attractiveness, purchase intention, and choice in travel decision-making. Two competing hypotheses (price association vs. fluency) were proposed. Across five empirical studies, we found that the perceived attractiveness of a price promotion deal, along with purchase intention and relative preference, were higher when the original price was presented in a rounded (vs. precise) format (Studies 1A, 1B, and 3). This finding supports the price association-based explanation rather than the fluency-based explanation. In addition, the results were replicated in a consequential choice setting (Study 2). We further demonstrated that the effect of the price rounding is stronger for those with high (vs. low) lay rationalism, suggesting its moderating role (Study 4). The empirical findings of the current research have theoretical implications for various fields, including the behavioral pricing of travel and tourism, and practical implications for practitioners.

Entropy profiles of Schelling’s segregation model from the Wang–Landau algorithm

We evaluate Schelling's segregation outcomes from the square lattice, regular random networks, and clustered regular random networks by situating them in the probability distribution of the entire outcome space of satisfaction and segregation. To do so, we employ the Wang-Landau algorithm and calculate the entropy and the number of states as a function of satisfaction and segregation. According to the results, satisfaction tends to increase with segregation, irrespective of the network structure. Moreover, segregation occurs almost surely when satisfaction is maximized, which we also algebraically derive and confirm on infinite-size networks. The average ratios of the neighbors of the same tag are about 67% for the square lattice and regular random networks and about 73% for clustered regular random networks with a clustering coefficient of 0.37(1). Thus, clustering increases segregation on regular random networks. Further, we find that Schelling's path-dependent process generates sharper segregation than expected by random configurations, an outcome symptomatic of over-optimization from the social welfare perspective. Adopting an alternative rule restricting individuals' choice set may reduce segregation without compromising on satisfaction.

What do Turkish, Spanish, and Pakistani medical students value in specialty training positions? A discrete choice experiment

Background:The aim of this study was to find out specialty training preferences of senior medical students from three medical schools in Turkey, Spain, and Pakistan.Methods:A Discrete Choice Experiment was carried out using an electronic form for students in three countries in 2021–2022 term. Each choice set in the form consisted of two hypothetical specialty training positions. The attributes were location, earnings, working conditions, personal perspective, quality of education, probability of malpractice, and prestige. Conditional logit model was used to estimate participants’ preferences and “willingness to accept” values.Results:The most valued attribute was “personal perspective on specialty area” for Turkish and Spanish students, while this attribute was not meaningful for Pakistani students. Turkish students needed a 204% of change in their income for a swap between the specialty that they like and not like. This tradeoff necessitated a 300% change for Spanish students. The most valued attribute for Pakistani students, which was “working conditions”, necessitated a 97% increase in income to switch from working in good conditions to working in poor conditions.Conclusion:In this first multinational DCE study in the medical education literature, we found the preferences of medical students in Turkey, Spain, and Pakistan are affected to various extents by several factors.

The influence of individualistic worldviews on severe weather preparation.

How do people think they should prepare for tornadoes? To answer this question, we surveyed 340 people in six states in tornado alley and presented eight severe weather preparation choice sets that varied short and long-term benefits and costs with benefits or to the individual or to the community. Fifty-six percent of respondents preferred tornado preparations for the long-term that benefit individuals rather than the community. Correlations between personal characteristics, future expectations, and an individual's preferred preparation strategy show that being married, expecting stronger tornados, and having an individualistic worldview significantly increased the choice of individual preparation options. Past tornado experience and one's current protection level were not significantly related to individual-minded preparation choices. Out of 18 independent variables analyzed, individual worldview was the best predictor of a person's preferences. Individual worldview by itself had better predictive power than a regression model that included an individual's socioeconomic status, past severe weather experience, expectations about future tornados, and current protective measures for severe weather by itself. These findings can inform elected officials considering public policies for natural disaster preparedness and deciding between tradeoffs for keeping government costs low or providing benefits for everyone in the community. Our results are useful for planners and emergency managers who develop strategies to encourage tornado preparation by citizens in the community. For example, emergency managers can replicate the study with options specific to their community to determine what government communications or actions could prompt individuals to put protective measures in place.