Choice Set Formation Research Articles

Probabilistic choice set formation incorporating activity spaces into the context of mode and destination choice modelling

Understanding the constraints that individuals face during their spatial choices is important from a policy perspective. Such constraints, however, are often overlooked in the choice set generation process during model development. In order to address that gap, the current study proposes a probabilistic choice set formation based on Manski's framework assuming that the actual choice set of an individual is latent (unobserved). Though latent class models with heterogeneous choice sets have been used previously in the context of mode and route choice, their application in the context of spatial choices have been hindered due to the inherently large choice sets making the problem computationally intractable. To address this issue, we propose to computationally simplify the problem by utilising the geography-derived notions of Activity Spaces to delineate a range of potential choice sets per individual helping us to capture both issues of spatial awareness and time-space constraints. In order to account for the latent nature of the true choice set, we propose a Latent Class Choice Modelling (LCCM) framework to allocate the individuals probabilistically into the different resulting choice sets, with each class having a different choice set and a different set of parameters. Thus the LCCM is able to capture heterogeneity in the choice sets and in the sensitivities, at the same time. The proposed LCCM framework is empirically tested on joint mode and shopping destination choices captured through a GPS smartphone application. It is compared to a base MNL model estimated on the global choice set, an LCCM capturing heterogeneity only in the sensitivities and a LCCM with latent consideration choice sets, similarly to the proposed model, but with generic parameters across classes. Our proposed specification is able to outperform all of the remaining models, while also providing insights on the factors affecting individuals to be constrained in their location choices across space hinting to cases of spatial cognition, the importance of the home and workplace geography and the individual's socioeconomic status. Such insights can be important for developing more behaviourally realistic models that can be used by planners and policy makers to formulate more effective measures that better relate to the underlying population. Furthermore, the analysis provides insights into the discrepancies that can emerge by accounting for latent consideration sets in willingness-to-pay measures and demand elasticities, which could have significant implications in the effectiveness of policy measures.

Simultaneous Capturing of a Flexible Substitution Pattern and the Complementary/Supplementary Relationship in a Consideration Set in Mode Choice Modeling by Using Stated Preference Data

This paper investigates the use of an elicited consideration set in a mathematical model of choice and consideration set formation. It proposes an econometric formulation by allowing unrestricted correlations among alternatives in the consideration set formation and a flexible substitution pattern in the choice model. Data from a stated preference (SP) survey is used where the SP choice tasks were followed by an elicitation of the consideration set while responding to the SP experiments. As opposed to the latent choice set formation approach, the elicited consideration set reduces the computational burden for model estimation. Empirical models reveal the benefit of modeling choice in conjunction with consideration of the set formation. It is evident that overlooking the probabilistic consideration set results in the over-estimation of the effects of key choice attributes, for example, travel time and generalized cost. Estimated correlations among alternatives in the consideration set formation revealed rich patterns of complementary and supplementary relationships among the alternatives that would not be possible to observe otherwise. However, it is also clear that the relationship in the consideration set formation may not be fully translated into substitution patterns in the choice model; that is explained by the error-component mixed logit model.

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.

Comparison of Fully Probabilistic and Partially Probabilistic Choice Set Models for Mode Choice

Contemporary models consider choice sets to be either fully deterministic or fully probabilistic. Deterministic choice set models do not account for stochasticity in the choice set formation, whereas probabilistic choice set models fail to recognize that exclusion and inclusion can be deterministic for some alternatives and individuals and yet random for others. A more general scenario is, therefore, where some alternatives are deterministically included or excluded and others probabilistically included. This paper proposes a richer framework that combines the features of both deterministic and probabilistic choice set models and explicitly allows an alternative to be deterministically included, deterministically excluded, or probabilistically considered in the choice set. This framework is better than the conventional models in four aspects: (a) the factors influencing consideration type are explicitly and parametrically analyzed instead of assumption as 0 or 1; (b) the specification can disentangle factors that affect the inclusion outcome from the type of consideration; and (c) the specification also permits differential sensitivity to factors in conditional choice probability among those who consider an alternative deterministically versus probabilistically. The partially probabilistic choice set model, a special case of the proposed generalized framework, developed using empirical data collected from working commuters in Chennai city, is benchmarked against the fully probabilistic choice set models. The results show that the former had improved goodness-of-fit, realistic consideration probability estimates, and better predictability of mode shares than the latter. Relevant policies have been evaluated by identifying the appropriate target segments at both the consideration and choice stages using the proposed model.

The Role of Attribute Screening and Choice Set Formation in Health Discrete Choice Experiments: Modeling the Impact of Benefit and Risk Attributes

ObjectivesThis study aimed to demonstrate the econometric modeling of benefit/risk-based choice set formation (CSF) within health-related discrete choice experiments. MethodsIn 4 different case studies, first, a trade-off model was fitted; building on this, a screening model was fitted; and finally, a full CSF model was estimated. This final model allows for attributes to be used first to screen out alternatives from choice tasks before respondents’ trade-off attributes and make a choice among feasible alternatives. Educational level and health literacy of respondents were accounted for in all models. ResultsModel fit in terms of log likelihood, pseudo-R2, Akaike information criterion, and Bayesian information criterion improved from using only trade-off or screening models compared with CSF models in 3 of the 4 case studies. In those studies, significant screening behavior was identified that (1) affected trade-off inferences, (2) rejects the pure trade-off model, and (3) supports the existence of screening on the basis of benefit-risk profiles, and other attributes. Educational level and health literacy showed significant interactions with multiple attributes in all case studies. ConclusionsChoice modelers should pay close attention to noncompensatory respondent behavior when they include benefit or risk attributes in their discrete choice experiment. Further studies should investigate why and when respondents undertake screening behavior. Screening behavior in choice data analysis is always a possibility, so researchers should explore extensions of econometric models to reflect noncompensatory behavior. Assuming that benefit and risk attributes will only affect trade-off behavior is likely to lead to biased conclusions about benefit or risk-based behavior.

Mechanisms Underlying Choice-Set Formation: The Case of School Choice in Chile

Many decisions involve selecting among many more options than an individual can effectively examine and consider. Therefore, people usually consider smaller and different “choice sets” as viable options. To better understand the processes affecting choice-set formation, we developed a computational model of how households become aware of potential choices in a context for which understanding household decision-making has important public policy implications: market-based reforms in education. In the model, households learn about the schools to which they can send their children through three mechanisms: find out about geographically proximate schools, access to publicly available information, and information gathered from interactions with other households. We calibrated the model using data from four cities in Chile, where students are not required to attend their neighborhood school. We then used the model to conduct hypothetical computational experiments that assessed how each mechanism impacted the sets of schools known to households before they make their choice (their “awareness set”). We found that the inclusion of a social interaction mechanism was crucial for producing simulated awareness sets that matched the awareness sets provided in a survey conducted by the Chilean Ministry of Education. We also found that the social interaction mechanism played the largest role in determining the quality and price range of the choices available in households’ awareness sets. Our findings highlight the importance of social interactions in a stage of decision-making before the direct impact of other individuals is typically made explicit. Moreover, it validates an approach that can be used in future models where understanding how decision-makers become aware of their options may be as important as the way they choose among them.

The evolution of choice set formation in dwelling and location with rising prices: A decadal panel analysis in the Greater Toronto Area

Home location choice is based on both the characteristics of the dwelling (e.g., size, style, number of bedrooms) and the location (e.g., proximity to work, quality of schools, accessibility). Recent years have seen a steep increase in the price of housing in many major cities. In this research, we examine how these price increases are affecting the types of dwelling and locations considered by households. A large sample of real estate listings from 2006 and 2016 from the Greater Toronto Area is used to develop the empirical models. Two recently developed discrete choice models are used in the study: a nested logit model with latent class feedback (LCF) and a semi-compensatory independent availability logit (SCIAL) model. A method of alternative aggregation is proposed to overcome the computational hurdle that often impedes the estimation of choice set models. We find a significant increase in the probability of larger households considering townhouses and apartments over detached single-family dwellings between 2006 and 2016.

Distortions in willingness-to-pay for public goods induced by endemic distrust in institutions

In this paper, we analyze the implications for the economic valuation of the provision of public goods, considering respondents’ perceptions of the institution(s) that provide the service. The specific behavioral mechanism whereby institutional distrust (ID) shows itself is through the activation of screening of choice options (choice set formation). However, ID-induced choice set formation might be confounded with the consumer budget constraint, especially in a developing country context, leading to biased welfare estimates for service improvement. We formulate a semi-compensatory hybrid choice set formation (SC-HCSF) model that enables us to 1) discriminate the effect of a budget constraint from that of ID-induced choice set formation and 2) characterize their separate impacts on welfare estimates using a spatial framework. We compare our model results to those from a standard Random Parameters Logit (RPL) Model. The RPL underestimates (overestimates) welfare when individuals have a low (high) ID. Based on our empirical model results, we demonstrate that the impacts of ignoring institutional trust issues can be highly deleterious to project appraisals, particularly in settings where legislative and regulatory institutions are perceived to be endemically corrupt.

Preferences for coastal and marine conservation in Vietnam: Accounting for differences in individual choice set formation

This paper has two objectives. The first is to estimate the value of implementing new coastal and marine conservation measures in Vietnam, focussing on the relative benefits of water quality improvements, coral conservation and control of marine plastic pollution. The second is to explicitly model any tendency of respondents to fail to give consideration to the “opt-out” or status quo option in a choice experiment, due to social and cultural factors. The analysis employs the independent availability logit model with random coefficients to simultaneously account for heterogeneity of preferences and choice set formation. Results show significantly improved model fit when consideration set heterogeneity is taken into account. However, estimates of preference weights and marginal willingness to pay for marine conservation measures are unaffected by this modelling choice.

Costly Consideration and Dynamic Choice Set Formation

Dynamic choices of cognitively constrained individuals have been ascribed, by the rational inattention theory, as being a filtering problem, in which the attentional intensity is consciously elected. Human attention, however, is not merely of voluntary intensity; it is rather of volitional placement nature. In this article, I study the implications of a dynamic theory of volitional attention describing individuals who choose among the alternatives that are induced by their attentional choices. Firstly, a consumer search application using US scanner data indicates that attentional choices are characterized by complementarities. Costs do not exclusively depend on the cardinality of consideration sets, but also on experience and similarities between considered items. Neglecting, thereby, attentional placement aspects potentially leads to misidentification of preference characteristics. Secondly, participation inertia in financial markets is revisited under the scope of volitional attention and a cultural-based argument of why it can be optimal not to participate is provided.

A semi-compensatory choice model with probabilistic choice set: combining implicit choice set within probabilistic choice set formation

A recent paper by Rashedi and Nurul Habib (2020) formulates a semi-compensatory choice model, a term originally conceived by Williams and Ortuzar (1982), later studied by Kawamoto and Setti (1992) ...

The experienced mode choice set and its determinants: Commuting trips in the Netherlands

Abstract Active modes take up an increasingly important place on the global policy-making agenda. In the Netherlands, a country that is well-known for its high shares of walking and cycling, the government aims at achieving a modal shift among 200,000 commuting car drivers towards using the bicycle. To this end, policy measures need to be introduced. When the aim is to achieve a modal switch over an enduring period of time, it is more relevant to know the likelihood of including or excluding a mode in the mode choice set, compared to choosing a mode for a single trip. Therefore, we investigate the formation of the experienced choice set (set of modes used over a long period of time), where the aim is to identify determinants that influence the inclusion or exclusion of a mode in this set. We estimate discrete choice models, based on survey data from the Netherlands Mobility Panel (MPN) and a complementary survey, where individuals were asked to report the frequency of using certain modes of transport for commuting trips over the course of half a year. This study shows that the experienced choice set for commuting is unimodal for the majority of the individuals, and remains constant over time for most individuals. Reimbursement by the employer for using a certain mode is the most important determinant influencing the experienced choice set, followed by ownership characteristics and urban density. We show that the mode choice set formation depends on more determinants than previously assumed.

A semi-compensatory choice model with probabilistic choice set: combining implicit choice set within probabilistic choice set formation

The standard random utility model assumes a fully rational and compensatory choice behaviour. However, various research studies have proven that non-compensatory /semi-compensatory choice behaviour is more realistic. This paper proposes a semi-compensatory framework for the discrete choice model that combines probabilistic choice set formation along with implicit choice constraints in choice making. It combines the Independent Availability Logit (IAL) with Implicit Constrained Multinomial Logit model (CMNL). The model is applied to investigate the mode choice behaviour of the Ottawa-Gatineau regions of Canada’s capital by using the household travel survey data. The explanatory power and elasticity measures of the proposed model are compared with IAL and MNL models. It is found that the IAL-CMNL model outperforms both IAL and MNL models and can reproduce the choice set formation process more effectively. The empirical investigation shows that the IAL-CMNL model results in relatively higher tolerance and softer constraints for cut-off violations compared to the IAL model. Elasticity calculations and outcomes of this research highlight the importance of capturing choice set formation and constrained choice behaviour in the choice modelling.

Social Cooperation in the Context of Integrated Private and Common Land Management

Several discrete choice experiment studies have investigated issues in the design of incentive programs to enhance the provision of ecosystem services. In these studies, ownership of land is usually private, and landowners make decisions independently of each other. However, the assumption of independence may be invalid when decision making involves a spatial setting and social networks. This study presents a new approach that accounts for social cooperation and preference interdependence across farmers in a land management context with mixed ownership. We formulate an econometric model of implicit choice set formation that accounts for (1) farmers’ expectations regarding mutual positive benefits from cooperation in an integrated land management system, and (2) the potential interdependence of preferences across farmers within the same socio-spatial group. We show that cooperation expectations matter for the decision of whether to engage in cooperative management and also for welfare estimates. Our model can identify sources of heterogeneities arising from cooperation expectations in ways that would not be possible using a reduced-form choice model. The assumption of independence should be checked routinely in similar settings to avoid potential endogeneity problems in discrete choice models when dealing with data that have a social-spatial dimension.

A two-stage recreational destination choice study incorporating fuzzy logic in discrete choice modelling

A major challenge in developing discrete choice models when the feasible choice set is extensively large is to find an appropriate choice set that is computationally manageable for being integrated into the choice modelling specification while it also reflects the behaviour of the decision-maker. This study aims to develop a new sampling method for choice set formation which is then used to improve the knowledge about recreational destination choice behaviour. The study proposes a two-stage framework where in the first stage a rule-based fuzzy logic model is used to form a latent choice set. The second stage incorporates the set in a discrete choice model to estimate destination selection behaviour. In the travel demand modelling literature, there has been little research into modelling recreational activity destination choices. In this area, the primary focus has been on other activities, such as work, study and shopping. In this context, the sampling methods used to form the choice set using the large set of possible options in the universal set are unconvincing. The proposed two-stage approach is examined using a household travel survey from Victoria, Australia, where nine different recreational destination choice models are developed. Compared to the conventional modelling framework, these models show impressive model fit and prediction potential.

Mode choice modelling for hailable rides: An investigation of the competition of Uber with other modes by using an integrated non-compensatory choice model with probabilistic choice set formation

This paper presents an empirical investigation on demand for TNC services (e.g., Uber) in the Greater Toronto and Hamilton Areas (GTHA) through the application of an innovative discrete choice model. The proposed model combines Independent Availability Logit (IAL) and Constrained Multinomial Logit (CMNL) model formulation to reap the unique features of both. The proposed model is thus a Semi Compensatory Independent Availability Logit (SCIAL) model. For the empirical investigation, it uses a dataset of trip mode choices that suitable to represent ride-hailing service (e.g., Uber). Such trips are named as hailable trips in the dataset, which is drawn from a large scale household travel survey conducted in the region in 2016. To have a clear understanding of behavioural processes involved in the choice of travel mode of hailable trips, the proposed SCIAL model jointly models probabilistic choice set formation and conditional semi-compensatory choice. The empirical model does not reveal any evident competition between Uber and the private car, public transit, or non-motorized modes. It indicates that urban taxi is its main competitor, but there are notable differences in socio-demographic profiles of taxi and Uber users. For example, a taxi is preferred by older people, but younger people prefer uber, and there is no gender difference in such a pattern. In terms of the relationship between considering Uber as a feasible mode and choosing it for a trip, Uber has similarities to the car passenger mode. Merely accepting it as a feasible option has a significant influence on the final choice to use it. This indicates a potential new segment of the travel market, generated primarily for the advent of TNC service, e.g., Uber in Toronto.

Choice Set Formation in Residential Mobility and Its Implications for Segregation Dynamics.

We develop and estimate a statistical model of neighborhood choice that draws on insights from cognitive science and decision theory as well as qualitative studies of housing search. The model allows for a sequential decision process and the possibility that people consider a small and selective subset of all potential destinations. When combined with data from the Los Angeles Family and Neighborhood Survey, our model reveals that affordability constraints and households' tendency toward short-distance moves lead blacks and Hispanics to have racially stratified choice sets in which their own group is disproportionately represented. We use an agent-based model to assess how racially stratified choice sets contribute to segregation outcomes. Our results show that cognitive decision strategies can amplify patterns of segregation and inequality.

Impact of Travel Time Constraints on Taste Heterogeneity and Non-Linearity in Simple Time–Cost Trade-Offs

Discrete choice models are a key technique for estimating the value of travel time (VTT). Often, stated choice data are used in which respondents are presented with trade-offs between travel time and travel cost and possibly additional attributes. There is a clear possibility that some respondents experience time constraints, leaving some of the presented options unfeasible. A model not incorporating information on these constraints would explain choices for faster and more expensive options as an indication that those respondents have a higher VTT when in reality they may be forced to select the more expensive option as a result of their personal constraints. This paper puts forward the hypothesis that this can have major impacts on findings in terms of heterogeneity in VTT measures. This paper examines via simulation the bias in VTT estimates and especially preference heterogeneity when such constraints are (not) accounted for. Empirical evidence is provided that preference heterogeneity is confounded with the travel budget impact on the availabilities of alternatives, and it is shown that there is a risk of producing biased estimates for appraisal VTT if studies do not explicitly model choice set formation. The inclusion of an opt-out alternative could be an effective measure to reduce the bias. This paper also explores the potential use of non-linear functional forms to capture the time budget impacts.

Analysis of the economic impact of water management policy on residential prices: Modifying choice set formation in a discrete house choice analysis

This paper extends discrete residential choice models by incorporating choice set formation. Most discrete residential choice models make relatively arbitrary assumptions about the choice set – the set of houses to be considered by the purchaser. In this paper we explore several formulations of endogenous choice sets in which the decision maker's selection of a choice set is based on certain attributes and the final selection is made from this reduced choice set. The proposed approach is empirically applied to a housing transaction dataset and welfare measures are generated for non-marginal changes associated with a water management policy. A comparison of models across different temporal windows to define an individual's choice set shows that model parameters are sensitive to the assumptions used to define the choice sets. The models that approximate choice set formation improve the efficiency of estimation and influence estimated welfare measures suggesting the importance of choice set formation in the context of discrete housing choice models.

Random taste heterogeneity in discrete choice models: Flexible nonparametric finite mixture distributions

This study proposes a mixed logit model with multivariate nonparametric finite mixture distributions. The support of the distribution is specified as a high-dimensional grid over the coefficient space, with equal or unequal intervals between successive points along the same dimension; the location of each point on the grid and the probability mass at that point are model parameters that need to be estimated. The framework does not require the analyst to specify the shape of the distribution prior to model estimation, but can approximate any multivariate probability distribution function to any arbitrary degree of accuracy. The grid with unequal intervals, in particular, offers greater flexibility than existing multivariate nonparametric specifications, while requiring the estimation of a small number of additional parameters. An expectation maximization algorithm is developed for the estimation of these models. Multiple synthetic datasets and a case study on travel mode choice behavior are used to demonstrate the value of the model framework and estimation algorithm. Compared to extant models that incorporate random taste heterogeneity through continuous mixture distributions, the proposed model provides better out-of-sample predictive ability. Findings reveal significant differences in willingness to pay measures between the proposed model and extant specifications. The case study further demonstrates the ability of the proposed model to endogenously recover patterns of attribute non-attendance and choice set formation.