Discrete Choice Methods Research Articles

Assessing the Cost of Large-Scale Power Outages to Residential Customers.

Residents in developed economies depend heavily on electric services. While distributed resources and a variety of new smart technologies can increase the reliability of that service, adopting them involves costs, necessitating tradeoffs between cost and reliability. An important input to making such tradeoffs is an estimate of the value customers place on reliable electric services. We develop an elicitation framework that helps individuals think systematically about the value they attach to reliable electric service. Our approach employs a detailed and realistic blackout scenario, full or partial (20 A) backup service, questions about willingness to pay (WTP) using a multiple bounded discrete choice method, information regarding inconveniences and economic losses, and checks for bias and consistency. We applied this method to a convenience sample of residents in Allegheny County, Pennsylvania, finding that respondents valued a kWh for backup services they assessed to be high priority more than services that were seen as low priority ($0.75/kWh vs. $0.51/kWh). As more information about the consequences of a blackout was provided, this difference increased ($1.2/kWh vs. $0.35/kWh), and respondents' uncertainty about the backup services decreased (Full: $11 to $9.0, Partial: $13 to $11). There was no evidence that the respondents were anchored by their previous WTP statements, but they demonstrated only weak scope sensitivity. In sum, the consumer surplus associated with providing a partial electric backup service during a blackout may justify the costs of such service, but measurement of that surplus depends on the public having accurate information about blackouts and their consequences.

Simulated exchange values and ecosystem accounting: Theory and application to free access recreation

This paper discusses the Simulated Exchange Value method, a practical method to estimate values for goods and services currently outside of the market in a manner consistent with the market-based figures considered in national accounts. The method proposes to simulate, in a partial equilibrium context, the price that would occur if a good or service outside of the market, such as free access recreation in forests, were internalized. The method takes into account the demand, estimated using non-market valuation techniques, the supply and the market structure. The discussion covers the case of a linear demand and the case in which the demand is estimated using discrete choice methods. This paper applies the method to free access recreation in the forests of Andalusia, in the south of Spain, and compares the results to those obtained using Hicksian variations.

Modeling the choice of time-of-day for joint social-recreational activities

In modeling time of day choice, constructing choice alternatives in the case of joint tours requires the temporal synchronization of travel of all members of the travel party. This study describes how the time constraints of multiple persons can be effectively accommodated into determining the choice set and, subsequently, the choice of timing for joint social/recreational tours. Many previous studies on time-of-day choice modeling have been dominated by dividing the continuous time variable into discrete time intervals. Although the continuous representation of time in the method was proposed, their relative complexity in the estimation over the discrete choice methods is a drawback from practical perspectives. In this study, an alternate two-step approach is proposed. The first model predicts the time-window chosen for pursuing the joint discretionary tour, and the second model locates the tour within the chosen time window by determining the start- and end-hours of the tour simultaneously on a continuous scale. A MNL model within the discrete contexture is also estimated as for the predictive assessment comparison. A wide set of explanatory variables were included in the model estimations. The models developed are used to assess predictive abilities using validation samples. Overall, the fractional-split model is shown to be effective from the standpoint of predictive accuracy over the reference model based on the discrete time representations.

Study of Bicycle Movements in Conflicts at Mixed Traffic Unsignalized Intersections

Mixed traffic is a common phenomenon in developing countries such as China. Understanding bicycles’ moving behavior when it conflicts with motor vehicles/bicycles/pedestrians at unsignalized intersections is important for developing mixed traffic flow simulation models. Observations and analysis of bicycle movements when they conflict with those of vehicles/pedestrians at mixed traffic unsignalized intersections were made in our study. Field data from actual bicycle movements were captured from video data. We then proposed a plausible cyclist conflict avoidance movement model in mixed traffic flow situations based on fuzzy logic and the discrete choice method. Field data were used for model calibration and validation, and the results were promising.

Analysis of post-disaster damage and disruptive impacts on the operating status of small businesses after Hurricane Katrina

When small businesses are impacted by natural hazard events, hazard and sociological researchers may have access to collect data from a sample of open businesses, in hopes of distilling lessons that might help reduce vulnerability to future disasters. Lessons from demised businesses might be more useful in reducing business closure for increasing business sustainability to disasters. Using interviews from a random sample of 371 open and 126 closed businesses’ experiences with Hurricane Katrina, discrete choice methods examine the relationship between the impact of post-disaster damage, loss of lifelines, types of delays in reopening, and cascading damages on business continuity. This unique sample offers the opportunity to determine whether damage to operating businesses was different than that of demised businesses. Respondents provided pre-Katrina data up through the last interviews in 2013. Results demonstrate that damage may have a short-term effect on operating status; it was associated with immediate demise but had much less effect on longer-term recovery. Additionally, it is evident that there is one path to failure. Businesses that did reopen, but later closed, may have been impacted by a cascade of both exogenous and endogenous shocks.

Head-to-head comparison of health-state values derived by a probabilistic choice model and scores on a visual analogue scale

BackgroundHealth states were quantified based on discrete choice (DC) modeling and visual analogue scale (VAS) values using the five-level version of the EQ-5D (EQ-5D-5L). The aim of this study was to determine the extent of the relationship between DC derived values (indirect method) and VAS values (direct method).MethodsData were collected in Canada, the United Kingdom, the Netherlands, and the United States. Respondents were asked to perform paired comparisons between two EQ-5D-5L health states for DC. In total, 400 different EQ-5D-5L states were included. After each DC task, respondents were prompted to score the two states one after another on a VAS. Intraclass correlation coefficients were calculated between DC and VAS values and illuminating graphs were designed.ResultsApproximately 400 respondents participated from each country. High similarity [individual intraclass correlation coefficients (ICC) >0.85] of DC and moderate correspondence of VAS values were observed for the four countries. Cross-country comparison of DC values shows a nonlinear relationship to the VAS values.ConclusionEQ-5D-5L derived DC and VAS values show a close but nonlinear relationship. Given the obvious biases associated with the VAS, DC methods based on ordinal responses may be a better alternative.

Quality of service and customer satisfaction: a conjoint analysis for the Nigerian bank customers

Purpose The purpose of this paper is to evaluate the perceptions of Nigerian banking customers regarding customers’ evaluation of their banks service quality based on their banks actual performance on current banking service delivery. Design/methodology/approach A survey has been used to collect primary data and 1,245 usable questionnaires were used in the analysis. A conjoint analysis with stated preference data were used to construct the consumers’ behavior, while discrete choice method was employed to evaluate the preferences. More information was obtained by in cooperating heterogeneity into the model by the random coefficient and the test variance with the primary attributes and social demographics and individual characteristics. Findings Discrete choice analysis shows that bank management should focus on: reduction of transaction errors, transaction cost, waiting time and initial online learning time. This four attributes have strong impact on customer’s satisfaction depending on quality performance. Relative to other services the reduction in waiting time and transaction cost are the most important services to the Nigerian banking customers. Other findings of willingness to pay and consumer preference for other attributes reveal more information for improved banking policies. Research limitations/implications The sample only focussed on the urban areas and did not consider rural dwellers. Future research should aim to improve on these by including a variable in the utility set up that captures the distance of the respondent to the main city. Practical implications Nigerian banking customers do not care about a friendly smile as customer care. Rather, they value more on the waiting time and transaction cost showing that convenience and cost dimensions have strong and direct effect on service quality. Other dimensions identified includes, reliability, product portfolio, security and privacy, ease of use, accessibility, and competence and credibility. Originality/value This study has drawn on a sample of 1,245 Nigerian banking customers and evaluating how the survey respondents perceive their respective banks’ performance by their evaluation of the current banking service delivery.

A Latent Class Nested Logit Model for Rank-Ordered Data with Application to Cork Oak Reforestation

We analyze stated ranking data collected from recreational visitors to the Alcornocales Natural Park (ANP) in Spain. The ANP is a large protected area which comprises mainly cork oak woodlands. The visitors ranked cork oak reforestation programs delivering different sets of environmental (reforestation technique, biodiversity, forest surface) and social (jobs and recreation sites created) outcomes. We specify a novel latent class nested logit model for rank-ordered data to estimate the distribution of willingness-to-pay for each outcome. Our modeling approach jointly exploits recent advances in discrete choice methods. The results suggest that prioritizing biodiversity would increase certainty over public support for a reforestation program. In addition, a substantial fraction of the visitor population are willing to pay more for the social outcomes than the environmental outcomes, whereas the existing reforestation subsidies are often justified by the environmental outcomes alone.

A survey on the impediments to low carbon technology investment of the petrochemical industry in Korea

Responding to the climate change, Korea has been establishing a domestic policy framework for promoting energy saving and greenhouse gases reduction, with the expansion of low carbon technologies for industry as a key area. This paper analyzes investment barriers for low carbon technology investment and suggests supportive policies based on a survey to petrochemical companies in Korea. A total of 35 samples were collected. Among which, 32 companies are targeted by the Korean domestic emission trading scheme and represent 63% of the total CO2 emissions of all petrochemical companies under this scheme. The analysis result indicates that low carbon technology introduction is not a priority for the sampled companies. Besides the lack of financial support, there exist other impediments to low carbon technology investment, e.g., lower investment priority, economic loss during new technology replacement, technology uncertainty and less pressure on energy prices. In addition, technology payback period acceptable for companies was estimated by the multi-bounded discrete choice method. The acceptable payback period on the part of half samples ranges from 2.4 to 3.6 years. The relatively high preference to short-term profitability of low-carbon technologies may hinder the companies to make the investment decision. Financial support and information dissemination for low carbon technologies may be useful to facilitate company's investment in low carbon technologies. Carbon pricing policies, such as emission trading scheme, is agreed to be supportive by providing the price signal for the investment. This analysis enhances the understating of Korean company's perception on low carbon technology investment and provides meaningful policy implications for the development and improvement of related policies.

Contingent valuation of urban public space: A case study of Ljubljanica riverbanks

The article presents an economic valuation of the Ljubljanica riverbanks area, which is an urban cultural landscape with distinct qualities of international importance. For this purpose, we combined a classical contingent valuation with a closed-form version of discrete choice method, where the protest responses have been removed. By using econometric analysis, we obtained the willingness-to-pay (WTP) value and established its determinants. It was ascertained that residents derived more utility from implementation of the targeted development scenario than visitors. Thus, a discriminatory contribution scheme similar to the one with respect to the mean WTP could supply substantial revenue for further targeted development, while still providing ample consumer surplus for both residents and visitors. The present analysis represents one of the method’s very few applications to urban landscape in Central and Eastern European countries.

Multinomial probit Bayesian additive regression trees.

This article proposes multinomial probit Bayesian additive regression trees (MPBART) as a multinomial probit extension of BART - Bayesian additive regression trees. MPBART is flexible to allow inclusion of predictors that describe the observed units as well as the available choice alternatives. Through two simulation studies and four real data examples, we show that MPBART exhibits very good predictive performance in comparison to other discrete choice and multiclass classification methods. To implement MPBART, the R package mpbart is freely available from CRAN repositories.

Use of discrete choice to obtain urban freight evaluation data

The ex-ante evaluation of urban freight solutions is a complex task, due to the interference of different stakeholder groups with different views and objectives. The multi-actor multi-criteria methods have developed as a response to this scenario, but the determination of the weights required by them remains an unclear and controversial task. We propose the use of discrete choice methods as a powerful tool to confront these multi-faced evaluation problems, since the resulting surveys are flexible and easy to respond, and do not give away the final quantitative results. We have applied this methodology to the selection of urban freight solutions in the city of Seville, in Spain, followed by the determination of the relative weights associated to different objectives, both analyses carried out from the side of the carriers stakeholder group.

A Comparison of Traditional and Discrete-Choice Approaches to the Analysis of Residential Mobility and Locational Attainment

This article contrasts traditional modeling approaches and discrete-choice models as methods to analyze locational attainment—how individual and household characteristics (such as race, socioeconomic status, age) influence the characteristics of neighborhoods of residence (such as racial composition and median income). Traditional models analyze attributes of a neighborhood as a function of the characteristics of the households within them; discrete-choice methods, on the other hand, are based on dyadic analysis of neighborhood attributes and household characteristics. I outline two problems with traditional approaches to residential mobility analysis that may be addressed through discrete-choice analysis. I also discuss disadvantages of the discrete-choice approach. Finally, I use data from the Panel Study of Income Dynamics to estimate residential mobility using traditional locational attainment and discrete-choice models; I show that these produce similar estimates but that the discrete-choice approach allows for estimates that examine how multiple place characteristics simultaneously guide migration. Substantively, these models reveal that the disproportionate migration of black households into lower-income tracts amounts to sorting of black households into black tracts, which on average are lower income.

Identifying a behaviourally relevant choice set from stated choice data

Stated choice experiments are designed optimally in a statistical sense but not necessarily in a behavioural choice making sense. Statistical designs, and consequently model estimation, assume that the set of alternatives offered in the experiment are processed by respondents with a specific processing strategy. Much has been studied about attribute processing using discrete choice methods in travel choice studies, but this paper focuses more broadly on processing of alternatives in the choice set offered in the experiment. This paper is motivated by the primary idea that the distribution of predicted choice probabilities associated with a set of alternatives defining a given choice set might provide strong evidence on the strategies that agents appear to use when choosing a preferred alternative. In an empirical setting of a choice set of size three, four model specifications are considered including a model for the selection of the best alternative in the full choice set and three variants of a best–worst regime. Using state choice data on road pricing reform, the empirical analysis examines which model specification delivers the most accurate prediction of the chosen alternative. The results suggest which alternatives really matter in choice making and hence the alternatives that might be included in a choice set for model specification.

Preferences of colorectal cancer patients for treatment and decision-making: a systematic literature review.

Treatment decisions in life-threatening diseases, like colorectal cancer (CRC), are crucial, since they have a great impact on patient's survival and health-related quality of life. Thereby, the inclusion of patient's preferences becomes more and more important; however, these first need to be identified. Therefore, we conducted a systematic literature review in 12 electronic databases, published between 2000 and 2012, in order to identify patient's preferences concerning treatment preferences and involvement in the decision-making process. Nineteen studies were included and thoroughly analysed. This review shows that CRC patients do have preferences regarding different treatment options and outcomes; however, these preferences are not homogenous and seem to depend on personal factors like age and gender. Despite the existence of these preferences, the majority of patients prefer a passive role in the decision-making process, which in part may be explained by the severity of the disease. Again, subgroup analyses reveal the impact of personal factors like gender and education on the preference. Due to the importance of personal factors in the analysis of patient preferences, we identified an urgent need for larger studies that are suitable for subgroup analyses and incorporate multi-attributive measurement techniques, like discrete choice methods.

A think aloud study comparing the validity and acceptability of discrete choice and best worst scaling methods.

ObjectivesThis study provides insights into the validity and acceptability of Discrete Choice Experiment (DCE) and profile-case Best Worst Scaling (BWS) methods for eliciting preferences for health care in a priority-setting context.MethodsAn adult sample (N = 24) undertook a traditional DCE and a BWS choice task as part of a wider survey on Health Technology Assessment decision criteria. A ‘think aloud’ protocol was applied, whereby participants verbalized their thinking while making choices. Internal validity and acceptability were assessed through a thematic analysis of the decision-making process emerging from the qualitative data and a repeated choice task.ResultsA thematic analysis of the decision-making process demonstrated clear evidence of ‘trading’ between multiple attribute/levels for the DCE, and to a lesser extent for the BWS task. Limited evidence consistent with a sequential decision-making model was observed for the BWS task. For the BWS task, some participants found choosing the worst attribute/level conceptually challenging. A desire to provide a complete ranking from best to worst was observed. The majority (18,75%) of participants indicated a preference for DCE, as they felt this enabled comparison of alternative full profiles. Those preferring BWS were averse to choosing an undesirable characteristic that was part of a ‘package’, or perceived BWS to be less ethically conflicting or burdensome. In a repeated choice task, more participants were consistent for the DCE (22,92%) than BWS (10,42%) (p = 0.002).ConclusionsThis study supports the validity and acceptability of the traditional DCE format. Findings relating to the application of BWS profile methods are less definitive. Research avenues to further clarify the comparative merits of these preference elicitation methods are identified.

Cellular Agent-Based Approach Incorporating Spatial Discrete Choice Methods

A cellular agent–based model was designed to simulate the potential land use impacts of the future high-speed rail (HSR) service on the city of Aveiro, Portugal, and its neighboring municipalities. The model incorporated a spatial discrete choice method as a submodel, which estimated land use evolution behavior based on the growth of socioeconomic variables and the increase of road and railway accessibility. For validation purposes, the model was first run to test the historical land use change in the study area from 1991 to 2011. Based on the validated model, an analysis of three scenarios with different hypothetical HSR station locations was implemented to estimate the future land use impacts of HSR between 2011 and 2031. The simulation revealed that the introduction of HSR service could offer great opportunities for land use development in the area and that the station location within the city of Aveiro showed relatively better attractiveness to the development of new urban fabric and commercial and industrial land covers.

Active Participation of Demand Through a Secondary Ancillary Services Market in a Smart Grid Environment

An optimization model that incorporates demand in the paradigm of smart grids and distributed generation is formulated. The objective is to transform the demand into an active agent that helps minimizing costs incurred by a distribution company for energy purchases and capacity payments, in a cost based marginal pricing scheme, also extrapolated to market based bids. The development of a secondary market for ancillary services offered by demand is proposed, with local intelligence and distributed generation, operating in a similar way to a day ahead market. Existing resources from the demand-side are provided to allow hourly market adjustments. The demand uncertain future is modeled via preference models using discrete choice methods. Portfolios of incentives, tailored to demand needs and preferences, are built. Consumption profiles of users are identified from synthetic curves and real consumption profiles, associated to large customers. NYISO time series data are used to illustrate the mechanism operation. The optimization model may be easily integrated into any management model of a market operator or within electricity distribution and traders. The only requirement for proper incorporation is the use of two-way communications for coordinating with the customers in the smart-grid and distributed generation paradigm.

ASSESSING PREFERENCES FOR COMPENSATION PACKAGES USING THE DISCRETE CHOICE METHOD: THE CASE OF THE BOLSA FLORESTA PROGRAM IN AMAZONAS, BRAZIL

Natural ecosystems, including forest ecosystems, continue to be degraded or converted at an alarming rate. To complement or substitute regulatory approaches to ecosystem management, market-based instruments such as "payments for ecosystem services" (PES) have been introduced and are gaining popularity. One of the prominent PES schemes in the world is the Bolsa Floresta Program (BFP) in the State of Amazonas, Brazil. The BFP was established by the Government of the State of Amazonas through its Secretariat for Environment and Sustainable Development in 2006 and is implemented by the Amazonas Sustainable Foundation. The BFP, which is a voluntary program to reduce deforestation and promote sustainable development by rewarding the communities for changing their land use practices, has four main components: the Bolsa Floresta Income; Bolsa Floresta Social; Bolsa Floresta Family; and Bolsa Floresta Association. A study was conducted to assess the preferences of the participating households in three reserves, namely: Rio Negro, Juma, and Uatumã, for different payment packages with varying combinations of the bolsas relative to the status quo option. The discrete choice method and an open ended question format were used to elicit the preferences of the participant households. The discrete choice model results showed that the majority of the respondents (about 80 per cent) in the three reserves chose an alternative which offered a 20 per cent increase in direct cash payments to households as their most preferred alternative. On the other hand, the majority of respondents who were subjected to open question stated that they would like to see an increase in benefits that fall under the Bolsa Floresta Social category.

A latent class choice based model system for railway optimal pricing and seat allocation

In this paper, discrete choice methods in the form of multinomial logit and latent class models are proposed to explain ticket purchase timing of passenger railway. The choice model and demand functions are incorporated into a revenue optimization problem which jointly considers pricing and seat allocation. The framework provides insightful policy implications in term of fare and capacity distribution derived from actual passenger behavior. It shows that accepting short-haul demand provides greater revenue than long-haul demand using the same capacity. Revenue improvement ranges from 16.24% to 24.96% in multinomial logit models and from 13.82% to 21.39% in latent class models respectively.