Discrete Choice Methods Research Articles

Preferences and valuation of small-scale wastewater treatment system maintenance using discrete choice method: Case of community-managed system in Jakarta, Indonesia

The focus of public service delivery on sustainability and universal access has enabled the enactment of many community-based programs in Indonesia. However, relevant studies that examine the willingness to pay among households that utilize community-managed facilities are lacking, despite it being one of the most important factors for maintenance and a strong indicator of commitment. In the present study, we aimed to estimate household users' preferences and willingness to pay (WTP) to understand their demand for related services. It estimates household user preferences and willingness to pay to understand the demand for related services through a choice experiment. By comparing all service attributes, the results highlight that users derive the highest utility if they updated reactors and pipelines, and, conversely, if the responsible authority is changed. The desire for quality improvement and service expansion were confirmed using this model. The mixed model estimated a willingness to pay of 0.03–3.13 USD for average users, depending on the attributes. Our findings confirm that families who belong to a community that operates a decentralized system derive greater benefits from improved maintenance; thus, they are willing to pay more to enjoy the service. Notably, at its core, a community-managed system, such as the Sanimas Program, is a co-production initiative between multiple levels of government institutions and local residents. Therefore, maintenance actions should involve resource- and payment-intensive efforts, such as half-year sanitary desludging and system replacement owing to deterioration and hazards. Policy regulations that correct the distribution of roles among partners for maintaining the system should be initiated. These findings provide evidence for the government's commitment to the community and could help convince other stakeholders to redirect their attention to supporting sustainable system performance.

Forest Owner Attitudes and Preferences for Voluntary Temporary Forest Conservation

This study explores attitudes and preferences of Finnish non-industrial private forest owners for voluntary temporary forest conservation. The survey data, collected with the best–worst scaling and discrete choice methods, focus on a conservation program that incentivizes forest owners for biodiversity conservation and carbon sequestration. Forest owners are willing to conserve simultaneously biodiversity and forest carbon. They prefer non-profit organization as implementer of program, suggesting alternative to current implementation of forest conservation by authorities. Forest owners’ interest in forest conservation program increases with shorter contract and higher payment, both aspects being subject to preference heterogeneity. Forest owners differ in terms of the perceived importance of ecological, economic and social aspects of sustainability of forestry. Heterogeneity in attitudes and preferences stems from the size of forest land, gender, freetime home located on forest site, and place of residence.

What do veterinary professionals and clients want? Using discrete choice methods in veterinary research to determine preferences.

Discrete choice methods (DCMs) are a suite of research techniques for identifying individual preferences using choice information. Widely utilized by other fields yet rarely employed in veterinary research, DCMs have tremendous potential to improve veterinary healthcare by understanding and incorporating owner and veterinary professionals' (encompassing veterinarians, veterinary clinicians, technicians, receptionists, attendants, etc) preferences to optimize the care continuum. DCMs have several advantages over other stated preference methods, such as ranking and ratings, including improved data quality and actionability. However, they are not a panacea, and limitations that may affect DCMs' application to the veterinary field are outlined alongside realistic mitigation strategies. The information provided aims to increase awareness of DCMs and their utility in veterinary research and encourage greater uptake as a more robust method for measuring preferences.

Reducing sample size requirements by extending discrete choice experiments to indifference elicitation

Discrete choice (DC) methods provide a convenient approach for preference elicitation and they lead to unbiased estimates of preference model parameters if the parameterization of the value function allows for a good description of the preferences. On the other hand, indifference elicitation (IE) has been suggested as a direct trade-off estimator for preference elicitation in decision analysis decades ago, but has not found widespread application in statistical analysis frameworks as for discrete choice methods. We develop a hierarchical, probabilistic model for IE that allows us to do Bayesian inference similar to DC methods. A case study with synthetically generated data allows us to investigate potential bias and to estimate parameter uncertainty over a wide range of numbers of replies and elicitation uncertainties for both DC and IE. Through an empirical case study with laboratory-scale choice and indifference experiments, we investigate the feasibility of the approach and the excess time needed for indifference replies. Our results demonstrate (i) the absence of bias of the suggested methodology, (ii) a reduction in the uncertainty of estimated parameters by about a factor of three or a reduction of the required number of replies to achieve a similar accuracy as with DC by about a factor of ten, (iii) the feasibility of the approach, and (iv) a median increase in time needed for indifference reply of about a factor of three. If the set of respondents is small, the higher elicitation effort may be worth to achieve a reasonable accuracy in estimated value function parameters.

Evaluation of open-ended, clustering, and discrete choice methods for user requirements development in a low-income country context

High quality user requirements are positively correlated with successful design outcomes, but engaging stakeholders within low-income contexts can present financial and time-related challenges to product developers from non-local industrial and academic institutions with limited knowledge of the context. Existing literature provides guidance for engaging stakeholders during the early stages of product design in high-income country contexts, but few studies have examined the effectiveness of these methods in low-income country contexts. This study evaluated three user requirements elicitation and prioritization methods including open-ended, clustering, and discrete choice. Ghanaian healthcare delivery stakeholders with varying types of expertise, years of experience, and from various types of healthcare facilities were recruited to allow for diversity of responses. Participants included physicians (n = 10), nurses/midwives (n = 16), biomedical technicians (n = 14), and public health officers (n = 7). A hypothetical mechanical device for managing and treating postpartum hemorrhage was chosen to characterize each method's ability to elicit and prioritize user requirements. The open-ended method captured general requirements of a design concept, yet resulted in predominantly generic requirements. The results from the open-ended method were used to inform the clustering and discrete choice methods. The clustering and discrete choice methods were useful for inferring in-depth user requirements and eliciting stakeholder priorities. The clustering method revealed that usability and affordability were high-priority requirements among all four stakeholder groups. An individual difference scaling analysis was performed using the clustering method outcomes, which indirectly identified ease-of-use, availability, and effectiveness as the priority user requirements categories. Stakeholders ranked ease-of-use as the highest-priority user requirement, followed by performance, cost, and place-of-origin requirements, using the discrete choice method. Given the significance of the ease-of-use requirement, an analytical framework based on sub-requirements was developed for quantifying stakeholder needs. Lastly, the relative merits of the three elicitation approaches and their implications for use with different stakeholder groups were examined.

Evaluating the Discrete Choice and BN Methods to Estimate Labor Supply Functions

Evaluating the Discrete Choice and BN Methods to Estimate Labor Supply Functions

Maximum Likelihood Estimation of Destination Choice Models with Constrained Attractions

Attraction constraints are common and often appropriate for destination choice models, including, but not limited to, doubly constrained gravity distribution models. Estimation of their parameters by discrete-choice methods, however, seldom accounts for the constraints, despite bias known from their omission. For multinomial logit destination choice, this paper first formulates the parameter estimation for maximum likelihood of a set of observations, subject to exogenous attraction constraints on the model’s application to a population. Second, this formulation is extended for attraction constraints being linear combinations of size variables with coefficients to be estimated. Both the utility and size parameter estimations are distinct from the well-known formulation for unconstrained estimation, because of the contribution of the constraining shadow-price utilities to the likelihood gradients. Gradients and the Hessian are identified, along with adaptations of them for Newton-Raphson parameter updates and Cramér-Rao bounds. Experiments demonstrate its computational tractability and performance, and compare its estimations with those of unconstrained and other methods.

Estimating welfare impacts of climate change using a discrete-choice model of land management: An application to western U.S. forestry

This study develops a method to estimate the welfare impacts of climate change on landowners using a discrete-choice econometric model of land management. We apply the method to forest management in the Pacific states of the U.S. and estimate welfare effects on the region that holds the largest current commercial value – western Oregon and Washington. We find evidence that a warmer and drier climate will induce an approximate 39 % loss in the economic value of timberland by 2050, though there is heterogeneity across space. The discrete-choice approach allows us to determine that the welfare losses are primarily driven by estimated losses to Douglas-fir, the most commercially valuable species. An alternative approach to welfare analysis from climate change is the Ricardian method, which gives conceptually similar estimates to the discrete-choice method. While we find similar empirical findings between the discrete-choice and Ricardian approaches, the discrete-choice approach provides more heterogeneity and somewhat larger negative welfare impacts. Our analysis is notable for providing the first empirical evidence that climate change can induce welfare losses to timberland owners, even while accounting for optimal adaptation.

Spatial‐Temporal Analysis of Crash Severity: Multisource Data Fusion Approach

High severity crashes are one of the negative consequences of suburban transportation for a range of factors. Fatalities, injuries, and medical costs, as well as road and car damage and mental side effects, are more important consequences of severe crashes. The goal of this research is to figure out what factors contribute to different crash severity levels, in order to reduce the likelihood of such crashes. This study is unique in that it tries to investigate the capabilities of various discrete choice methods in order to explore which one performs best given the current database and research restrictions. Furthermore, the data fusion approach allows this study to take advantage of a wide range of characteristics that influence crash severity. To achieve this objective, the current study used several types of discrete choice models, such as ordered logit (OL), multinominal logit (MNL), and mixed logit (ML) models, to examine the factors influencing the severity of crashes in the suburban highway area. The data are related to crashes and traffic counters in Khorasan Razavi province in the northeast of Iran. Spatial‐temporal analysis of crash data with a data fusion approach has been conducted to prepare a multisource data set with a wide spectrum of independent variables to acquire reliable results using logit models. Independent descriptive variables include geometric design, time‐related, weather and environmental conditions, land use, traffic attributes, vehicle characteristics, and driver characteristics. ML provided the best fit with the available data set when compared to other discrete choice techniques. In addition, in all three logit models, coefficients of geometric design, vehicle characteristics, driver characteristics, land use, and weather and environmental conditions are significant, demonstrating the significance of using multisource data in defining factors impacting crash severity.

Student’s Preferences in the Selection of Online Shopping Goods Delivery Services

(The rise of e-commerce or online shops has made the number of shipping service companies increase. Delivery service companies need to analyze consumer preferences in selecting delivery services when shopping online so that they can continue to compete. This study aims to analyze the attributes or important factors that influence consumers and how much influence these factors have on consumer preferences. The AHP (Analytical Hierarchy Process) method is used to obtain the important factors and the discrete choice method with the multinomial logit model to analyze the influence of factors on consumer preferences. With the AHP method, three important attributes are obtained including cost with a value of 4.248, insurance with a value of 1.729, and delivery time with a value of 1.471. Judging from the influence on preferences, the cost factor and delivery time have a negative effect, which means that the lower the rate and the faster the time will increase customer satisfaction. While the insurance factor has a positive effect, which means that consumers prefer insurance. The most influential factor is cost with a parameter value of -1.97, then insurance with a parameter value of 1.66, and finally delivery time with a parameter value of -0.564. Based on gender, the results show that women's considerations of the cost attribute are higher than men's considerations. Meanwhile, based on allowance, the higher the allowance, the more important insurance and delivery time are considered.

Modeling hesitancy in airport choice: A comparison of discrete choice and machine learning methods

Noticing that people may become more hesitant about their airport choice when exposed to abundant information and multi-channel on-line sales opportunities, this paper analyzes hesitancy in the choice of transfer airport in a multi-airport region using three approaches: a multinomial logit model, a random forests algorithm, and deep reinforcement learning. These methods are applied to the outcomes of a stated choice experiment, which was designed to survey the iterative airport choice process under hesitancy. The results indicate that a quarter of the passengers show evidence of hesitancy. Further, the deep reinforcement learning approach is found to provide the highest accuracy in representing the stated choices; the random forests algorithm also gives good results in capturing the reconsideration decision, while the multinomial logit model seems less accurate in representing the choice behavior of interest. Moreover, hesitancy involved a switch from flight-related attributes to ground transport-related attributes. Managerial implications for airlines and airports are discussed.

The construction workers’ preference and acceptance of innovations in data provision: A stated choice experiment study in the Netherlands

Building information modeling (BIM) and Augmented Reality (AR) have many potential benefits if it can be implemented on the construction site. However, the adoption is very limited so far. Till now, construction workers get information mostly in a paper-based format, which is an obstacle for innovation implementation on site. To identify which forms of data provision are more preferred, and which attributes would influence construction workers’ acceptance of innovations on-site, this paper reports the results of two stated choice experiments using discrete choice methods. A total of 160 valid respondents were recruited from construction sites in the Netherlands to complete an online experiment. The mixed logit (ML) model was estimated to unravel construction workers’ preferences. The results show that construction workers are willing to accept new forms of data provision and new technologies in general. They are more likely to accept innovation if there is enough guidance.

Quantifying expert opinion with discrete choice models: Invasive elodea's influence on Alaska salmonids

Scientific evidence should inform environmental policy, but rapid environmental change brings high ecological uncertainty and associated barriers to the science-management dialogue. Biological invasions of aquatic plants are a worldwide problem with uncertain ecological and economic consequences. We demonstrate that the discrete choice method (DCM) can serve as a structured expert elicitation alternative to quantify expert opinion across a range of possible but uncertain environmental outcomes. DCM is widely applied in the social sciences to better understand and predict human preferences and trade-offs. Here we apply it to Alaska's first submersed invasive aquatic freshwater plant, Elodea spp. (elodea), and its unknown effects on salmonids. While little is known about interactions between elodea and salmonids, ecological research suggests that aquatic plant invasions can have positive and negative, as well as direct and indirect, effects on fish. We use DCM to design hypothetical salmonid habitat scenarios describing elodea's possible effect on critical environmental conditions for salmonids: prey abundance, dissolved oxygen, and vegetation cover. We then observe how experts choose between scenarios that they believe could support persistent salmonid populations in elodea-invaded salmonid habitat. We quantify the relative importance of habitat characteristics that influence expert choice and investigate how experts trade off between habitat characteristics. We take advantage of Bayesian techniques to estimate discrete choice models for individual experts and to simulate expert opinion for specific environmental management situations. We discuss possible applications and advantages of the DCM approach for expert elicitation in the ecological context. We end with methodological questions for future research.

Developing a New Version of the SF-6D Health State Classification System From the SF-36v2: SF-6Dv2.

The objective of this study was to develop the classification system for version of the SF-6D (SF-6Dv2) from the SF-36v2. SF-6Dv2 is an improved version of SF-6D, one of the most widely used generic measures of health for the calculation of quality-adjusted life years. A 3-step process was undertaken to generate a new classification system: (1) factor analysis to establish dimensionality; (2) Rasch analysis to understand item performance; and (3) tests of differential item function. To evaluate robustness, Rasch analyses were performed in multiple subsets of 2 large cross-sectional datasets from recently discharged hospital patients and online patient samples. On the basis of factor analysis, other psychometric evidence, cross-cultural considerations, and amenability to valuation, the 6-dimension classification used in SF-6D was maintained. SF-6Dv2 resulted in the following modifications to SF-6D: a simpler classification of physical function with clearer separation between levels; a more detailed 5-level description of role limitations; using negative wording to describe vitality; and using pain severity rather than pain interference. The SF-6Dv2 classification system describes more distinct levels of health than SF-6D, changes the descriptions used for a number of dimensions and provides clearer wording for health state valuation. The second stage of the study has developed a utility value set using discrete choice methods so that the measure can be used in health technology assessment. Further work should investigate the psychometric characteristics of the new instrument.

The Potential Supply and Demand of Farmers’ Land Contract Rights-Based on 697 Households in Four Provinces of China

A new urbanization and rural revitalization strategy has been implemented in China over a number of years, under which farmers’ land contract rights (LCRs) flow inevitably through various means. The practice in reform pilot areas indicates that government funds cannot meet all the needs, so exploring market-based LCR payout paths is important for rural land tenure system reform. The purpose of this study is to answer questions such as the following: How would farmers respond if they were allowed to trade LCRs? Is there an equilibrium point between the potential supply and demand of LCRs? Which factors would affect the potential supply and demand of LCRs? In this study, 697 valid questionnaires from Ningxia, Hebei, Henan, and Shandong provinces, China, were used for analysis by the multiple bounded discrete choice (MBDC) method and MBDC-Tobit model. The results show that there is a potential market among rural collective households in China, with an equilibrium price of ¥27,800/mu ($59,714.4/ha), and a proportion of farmers who are willing to buy or sell LCRs is around 10.0%. The factors affecting the potential supply and demand of LCRs include land grade, average agricultural income per unit, total money to buy urban houses and cars, age, number of household members with a college education or above, and risk appetite. If the institutional barriers that hinder LCR transactions were eliminated, the potential supply and demand of LCRs would be matched, and the market would provide funds for next-stage reforms.

Pakiet conjoint programu R jako narzędzie pomiaru preferencji wyrażonych

Two groups of research methods are used in the decompositional approach to stated preferences – conjoint analysis methods and discrete choice methods. The most commonly applied traditional conjoint analysis method is an example of the first group. Because of its computational complexity, its practical application requires using appropriate commercial or non-commercial computer software. The purpose of the article is to present the traditional conjoint analysis method and discuss its implementation in the form of the conjoint package for R program, which with CRAN packages is currently one of the most important non-commercial computing environments for statistical data analysis. In addition to the detailed characteristics of the individual conjoint R package functions, the paper also presents the application of the conjoint package in marketing research, along with the interpretation of the selected results, based on the example of measuring and analysing stated preferences of beer consumers

Dental Hygienists' and Dentists' Tobacco Cessation Continuing Education Preferences: Application of a Discrete Choice Method.

Despite ample opportunity, dental professionals frequently fall short of connecting tobacco-using patients with effective cessation support, often citing lack of training as a barrier. To inform development of training options, the aim of this study was to quantify the preferences of practicing dental hygienists and dentists in California for continuing dental education (CDE) offerings related to tobacco and patient tobacco cessation. Two statewide surveys of California dental hygienists and dentists were conducted. In addition to providing their own and their practice characteristics, in a discrete choice experiment, participants indicated their preferences between pairs of randomly generated hypothetical tobacco cessation CDE offerings that differed in topic, cost, delivery modality, and duration. Ultimately, 641 dental hygienists (20.5% of the total invited minus those with undeliverable emails, n=3,129) and 654 dentists (8.5% of the total invited minus those with undeliverable emails, n=7,669) responded to at least one of the discrete choice items, and their responses were analyzed. The results showed that each CDE attribute was independently associated with preference. Cost and topic were more strongly associated with preference than were delivery modality and duration. Lower cost, shorter duration courses were generally favored. Alternative tobacco products and patient communication were the most popular topics for participating dental hygienists and dentists, respectively. CDE preferences differed according to participant characteristics: live webinars were the least preferred modality for more experienced dental professionals, and shorter courses were not preferred by dentists in non-urban locations. These findings showed that these dental professionals considered multiple attributes in selecting CDE courses. To reach the broadest audience, CDE providers should offer low-cost options across a range of delivery modalities, such as full-day workshops in rural areas and online webinars for earlier career professionals.

Understanding patients’ values and preferences regarding early stage lung cancer treatment decision making

IntroductionWith advances in treatments among patients with lung cancer, it is increasingly important to understand patients’ values and preferences to facilitate shared decision making. MethodsProspective, multicenter study of patients with treated stage I lung cancer. At the time of study participation, participants were 4–6 months posttreatment. Value clarification and discrete choice methods were used to elicit participants’ values and treatment preferences regarding stereotactic body radiation therapy (SBRT) and surgical resection using only treatment attributes. ResultsAmong 114 participants, mean age was 70 years (Standard Deviation = 7.9), 65% were male, 68 (60%) received SBRT and 46 (40%) received surgery. More participants valued independence and quality of life (QOL) as “most important” compared to survival or cancer recurrence. Most participants (83%) were willing to accept lung cancer treatment with a 2% chance of periprocedural death for only one additional year of life. Participants also valued independence more than additional years of life as most (86%) were unwilling to accept either permanent placement in a nursing home or being limited to a bed/chair for four additional years of life. Surprisingly, treatment discordance was common as 49% of participants preferred the alternative lung cancer treatment than what they received. ConclusionsAmong participants with early stage lung cancer, maintaining independence and QOL were more highly valued than survival or cancer recurrence. Participants were willing to accept high periprocedural mortality, but not severe deficits affecting QOL when considering treatment. Treatment discordance was common among participants who received SBRT or surgery. Understanding patients’ values and preferences regarding treatment decisions is essential to foster shared decision making and ensure treatment plans are consistent with patients’ goals. Clinicians need more resources to engage in high quality communication during lung cancer treatment discussions.

Comparing Survival Analysis and Discrete Choice Specifications Simulating Dynamics of Vehicle Ownership

Modeling travel-related decisions of transport system users is the core of many behavioral travel demand models. It is of great significance to use these models for planning purposes in which decisions of individuals are simulated for specific time intervals or on a continuous dimension until the target year. Discrete choice and survival analysis methods are two popular econometric structures to model and forecast time-dependent outcomes. This paper elaborates the conceptual and practical differences between these two methods in the context of vehicle ownership modeling. There are meaningful differences between these two methods including data preparation approaches, interpretations of the variable of interest in the model, and the simulation procedures. Further, this paper shows how negligent application of discrete choice methods for modeling time-to-event variables results in specification bias. This discussion paves the path for using hazard-based models in travel demand modeling, as the application of these models have been quite limited compared with their capacity.

Prioritizing professional competencies in environmental public health: A best–worst scaling experiment

The professional development of environmental public health professionals in Canada is guided by a set of 133 discipline-specific competencies. Given the diversity of practice in environmental public health, certain competencies may be more important to job effectiveness depending on a practitioner’s context. However, the most important competencies to job effectiveness by context are unknown. Thus, the objectives of this study were to prioritize the discipline-specific competencies according to their importance to job effectiveness, and determine if importance varied by demographic variables. A quantitative discrete-choice method termed best–worst scaling was used to determine the relative importance of competencies. Discrete choice information was electronically collected and analyzed using Hierarchical Bayesian analysis. Our analysis indicates that communication was most important to job effectiveness relative to the other categories. Competency statements within each category differed in their importance to job effectiveness. Further, management and front-line practitioners differed in the importance placed on five of the eight categories. This information can be used to guide new training opportunities, thereby investing in the capacity of environmental health professionals to better protect population health.