Experimental analysis of choice

Carson, Richard T.; Louviere, Jordan J.; Anderson, Donald A.; Arabie, Phipps; Bunch, David S.; Hensher, David A.; Johnson, Richard M.; Kuhfeld, Warren F.; Steinberg, Dan; Swait́, Joffre; Timmermans, Harry; Wiley, Jennifer

doi:10.1007/bf00999210

Cited by 267 publications

(148 citation statements)

References 27 publications

Supporting

Mentioning

145

Contrasting

Unclassified

Order By: Relevance

“…Byrne, Amer, Fennessy, Hansen and Wickham In this respect, prior consultation with industry experts and pilot-testing of the survey proved to be very useful for specifying relevant and well-defined attributes and levels. Carson et al (1994) argues that a lack of sufficient variation in the levels exhibited by an attribute in actual (i.e. observed) market data is one of the main reasons for using choice experiments, as such variation can be controlled in preference-based surveys.…”

Section: Study Technique and Methodologymentioning

confidence: 99%

A preference-based approach to deriving breeding objectives: applied to sheep breeding

Byrne

Amer²,

Fennessy³

et al. 2012

Animal

View full text Add to dashboard Cite

Using internet-based software known as 1000Minds, choice-experiment surveys were administered to experts and farmers from the Irish sheep industry to capture their preferences with respect to the relative importance -represented by part-worth utilitiesof target traits in the definition of a breeding objective for sheep in Ireland. Sheep production in Ireland can be broadly separated into lowland and hill farming systems; therefore, each expert was asked to answer the survey first as if he or she were a lowland farmer and second as a hill farmer. In addition to the experts, a group of lowland and a group of hill farmers were surveyed to assess whether, and to what extent, the groups' preferences differ from the experts' preferences. The part-worth utilities obtained from the surveys were converted into relative economic value terms per unit change in each trait. These measures -referred to as 'preference economic values' (pEVs) -were compared with economic values for the traits obtained from bio-economic models. The traits 'value per lamb at the meat processor' and 'lamb survival to slaughter' were revealed as being the two most important traits for the surveyed experts responding as lowland and hill farmers, respectively. In contrast, 'number of foot baths per year for ewes' and 'number of anthelmintic treatments per year for ewes' were the two least important traits. With the exception of 'carcase fat class' (P , 0.05), there were no statistically significant differences in the mean pEVs obtained from the surveyed experts under both the lowland and hill farming scenarios. Compared with the economic values obtained from bio-economic models, the pEVs for 'lambing difficulty' when the experts responded as lowland farmers were higher (P , 0.001); and they were lower (P , 0.001) for 'carcase conformation class', 'carcase fat class' (less negative) and 'ewe mature weight' (less negative) under both scenarios. Compared with surveyed experts, pEVs from lowland farmers differed significantly for 'lambing difficulty', 'lamb survival to slaughter', 'average days to slaughter of lambs', 'number of foot baths per year for ewes', 'number of anthelmintic treatments per year for ewes' and 'ewe mature weight'. Compared with surveyed experts, pEVs from hill farmers differed significantly for 'lambing difficulty', 'average days to slaughter of lambs' and 'number of foot baths per year for ewes'. This study indicates that preference-based tools have the potential to contribute to the definition of breeding objectives where production and price data are not available.

show abstract

Section: Study Technique and Methodologymentioning

confidence: 99%

A preference-based approach to deriving breeding objectives: applied to sheep breeding

Byrne

Amer²,

Fennessy³

et al. 2012

Animal

View full text Add to dashboard Cite

show abstract

“…Choice-based conjoint analysis has become very popular both among practitioners and academics (Carson et al, 1994;Louviere, Hensher, and Swait 2000). We now discuss how to modify the RR-Het method for choice data.…”

Section: Choice-based Conjoint Estimation Methodsmentioning

confidence: 99%

“…We label this model Metric Bayes-CV. 8 Unfortunately, such closed-form expressions are only available for metric data and not for choice data. Hence we are unable to test an equivalent model for choice (note that the second practical problem would remain even if we were able to address the first).…”

Section: Using Cross-validation To Select the Parameters Of The Seconmentioning

confidence: 99%

A Convex Optimization Approach to Modeling Consumer Heterogeneity in Conjoint Estimation

Evgeniou

Pontil

Toubia³

2007

Marketing Science

107

View full text Add to dashboard Cite

We propose and test a new approach for modeling consumer heterogeneity in conjoint estimation, which extends individual-level methods based on convex optimization and statistical machine learning. We develop methods both for metric and choice data. Like HB, our methods shrink individual-level partworth estimates towards a population mean. However, while HB samples from a posterior distribution that depends on exogenous parameters (the parameters of the second-stage priors), we minimize a convex loss function that depends on an endogenous parameter (determined from the calibration data using cross-validation). As a result, the amounts of shrinkage differ between the two approaches, leading to different estimation accuracies. Comparisons based on simulations as well as empirical data sets suggest that the new approach overall outperforms standard HB (i.e., with relatively diffuse second-stage priors) both with metric and choice data.

show abstract

“…The approach has been applied extensively within inter alia transport studies (pionered by McFadden 1974), marketing (see e.g. Carson et al 1994) and valuation of non-market goods(e.g. Hanley et al 1998;Carlsson and Martinsson 2001;Campbell et al 2008 …”

Section: Choice Experimentsmentioning

confidence: 99%