Attributes In Choice Experiments Research Articles

Testing for saliency-led choice behavior in discrete choice modeling: An application in the context of preferences towards nuclear energy in Italy

This work proposes a discrete choice model that jointly accounts for heterogeneity in preferences and in decision making procedures adopted by respondents, as well as for non-linearities in the utility function, allowing for the potential effect of salient attributes in choice experiments. We present an innovative application in the context of preferences towards nuclear energy, with data obtained from a nationwide online survey conducted in Italy. Results show that most of the variation in the choice data is indeed due to heterogeneity in the decision process, where the saliency heuristic plays an important role. Furthermore, the proposed model provides more conservative monetary valuations as opposed to standard models, potentially leading to substantial differences in cost-benefit analysis. Implications for choice modeling practitioners are discussed, emphasizing the need to account for saliency effects when modeling the choice data.

Congestion management in protected areas: accounting for respondents’ inattention and preference heterogeneity in stated choice data

Abstract Congestion levels in protected areas can be predicted by destination choice models estimated from choice data. There is growing evidence of subjects’ inattention to attributes in choice experiments. We estimate an attribute non-attendance latent class–random parameters model (LC–RPL) that jointly handles inattention and preference heterogeneity. We use data from a choice experiment designed to elicit visitors’ preferences towards sustainable management of a protected area in the Italian Alps. Results show that the LC–RPL model produces improvements in model fit and reductions in the implied rate of inattention, as compared to traditional approaches. Implications of results for park management authorities are discussed.

WTP for baby milk formula in China: Using attribute nonattendance as a priori information to select attributes in choice experiment

AbstractIt is well‐known that these nonattended attributes in choice experiments (CE) could cause some bias. A combination of two successive CEs are designed with focus on consumers’ demand for the attributes of baby milk formula in China, where the first CE includes the full set of attributes and the second excludes consumers’ self‐reported nonattended attributes in the first CE. Significant discrepancies are detected for both WTPs for an individual attribute and the total WTPs (the sum of all WTPs for individual attributes in each CE), and in most cases WTPs decrease as a result of excluding the ignored attributes. Changes in WTP are mainly driven by the variation of choice task complexity. However, there is no significant difference in the influence of excluding nonattended attributes on the WTPs for the same attended attribute in different subsamples. In addition, we also find that consumers in China have significantly higher but dispersed WTP values for imported (11.6–47.0%), organic (6.9–52.5%), and probiotics (7.3–35.5%) and sugar‐free (5.9–26.0%) attributes for baby milk formula. [EconLit citations: C90, D12, Q13, Q18].

Cue versus independent food attributes: the effect of adding attributes in choice experiments

We examine the effects of adding an independent food attribute on consumers’ willingness to pay (WTP) estimates for both cue and independent food attributes. In three separate choice experiments, a cue attribute present along the entire sequence of choices had independent food attributes enucleated and made explicit from the cue at later stages. Logit models were estimated using (i) a complete panel approach; (ii) error components and (iii) utility in WTP-space. Results suggest that the way a subject processes food attributes depends not only on the design dimensions but also on food attributes’ functional roles. When complexity of designs increases, models that account for different sources of heterogeneity have better fit to the data.

What are the consequences of ignoring attributes in choice experiments? Implications for ecosystem service valuation

This paper investigates the sensitivity of choice experiment values 3AL for ecosystem services to ‘attribute non-attendance’. We consider three cases of attendance, namely that people may always, sometimes, or never pay attention to a given attribute in making their choices. This allows a series of models to be estimated which addresses the following questions: To what extent do respondents ignore attributes in choice experiments? What is the impact of alternative strategies for dealing with attribute non-attendance? Can respondents reliably self-report non-attendance? Do respondents partially attend to attributes, and what are the implications of this? Our results show that allowing for the instance of ‘sometimes attending’ to attributes in making choices offers advantages over methods employed thus far in the literature.

Modelling Mode Choice in Passenger Transport with Integrated Hierarchical Information Integration

The Integrated Hierarchical Information Integration (HII-I) approach allows to include a larger number of attributes in choice experiments by summarising similar attributes into constructs. In separate sub-experiments, one construct is described by its attributes while the other constructs are included by summarising construct values. This approach allows for testing of process equality in order to know if the different sub-experiments may be concatenated into an overall model.In this paper, the HII-I approach is applied to model the mode choice between a regional train, a (hypothetical) regional bus and a car (only available for car users). Test results show that process equality is given when analysing only the data of the bi-modal sub-experiments whereas the assumption of process equality is rejected for data of the tri-modal sub-experiments, where differences in error variances between the sub-experiments are found. This empirical finding suggests that it is possible to construct separate sub-experiments while arriving at a single concatenated model.

Dealing with Ignored Attributes in Choice Experiments on Valuation of Sweden’s Environmental Quality Objectives

Using a choice experiment, this paper investigates how Swedish citizens value three environmental quality objectives. In addition, a follow-up question is used to investigate whether respondents ignored any attributes when responding. The resulting information is used in model estimation by restricting the individual parameters for the ignored attributes to zero. When taking the shares of respondents who took both the environmental and the cost attributes (52–69% of the respondents) into account, then the WTP for each attribute changes if the respondents who ignored the attributes have a zero WTP. At the same time, we find evidence that not all respondents who claimed to have ignored an attribute really did. However, the most commonly ignored non-monetary attributes always have the lowest rankings in terms of WTP across all three environmental objectives. Thus, our results show that instead of ignoring attributes completely, respondents seem to put less weight on the attributes they claimed to have ignored.

Modeling the effects of including/excluding attributes in choice experiments on systematic and random components

This paper examines the impact of attribute presence/absence in choice experiments using covariance heterogeneity models and random coefficient models. Results show that attribute presence/absence impacts both mean utility (systematic components) and choice variability (random components). Biased mean effects can occur by not accounting for choice variability. Further, even if one accounts for choice variability, attribute effects can differ because of attribute presence/absence. Managers who use choice experiments to study product changes or new variants should be cautious about excluding potentially essential attributes. Although including more relevant attributes increases choice variability, it also reduces bias.