Adjusting Choice Models to Better Predict Market Behavior

Allenby, Greg M.; Fennell, Geraldine; Huber, Joel; Eagle, Thomas C.; Gilbride, Tim; Horsky, Dan; Kim, Jaehwan; Lenk, Peter; Johnson, Richard M.; Ofek, Elie; Orme, Bryan; Otter, Thomas; Walker, Joan L.

doi:10.1007/s11002-005-5885-1

Cited by 68 publications

(62 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…5 The function is typically, U=ΣXβ, where X's are attributes or functions of attributes such as X 1 X 2 . 6 Liu and Arora [115] found asymmetric effects in design efficiency loss. When the true model is conjunctive, compensatory designs have significant loss of design efficiency.…”

Section: Suggested Directions For Future Researchmentioning

confidence: 99%

“…Yet, noncompensatory simple heuristics are often more or at least equally accurate in predicting new data compared to linear models that are criticized for over-fitting the data [67,89,103]. While the linear utility model has been the mainstay in conjoint research, Bayesian methods, including data augmentation, can easily accommodate nonlinear models and can deal with irregularities in the likelihood surface [6]. Recently, Kohli and Jedidi [103] and Yee et al [190] propose dynamic programming methods (using greedy algorithm) to estimate lexicographic preference structures.…”

Section: A2 Compensatory Versus Noncompensatory Processesmentioning

confidence: 99%

“…Recently, Hauser et al [76] propose two machine-learning algorithms to estimate cognitively simple generalized disjunctions-ofconjunctions (DOC) decision rules, and Liu and Arora [114] develop a method to construct efficient designs for a twostage, consider-then-choose model. 6 Stuttgen et al [164] propose a continuation of the line of research started by Gilbride and Allenby [67] and Jedidi and Kohli [89] that does not rely on compensatory trade-offs at all. These finding are consistent with economic theories of consideration set wherein consumers balance search costs with option value of utility maximization to achieve cognitive simplicity.…”

Section: A2 Compensatory Versus Noncompensatory Processesmentioning

confidence: 99%

“…Both stated and revealed preference data provide information on the utility of offerings, and thus one source of data can be integrated as a covariate in a model of the other [82]. Further, Allenby et al [6] recommend that information across datasets may be combined by forming a joint likelihood function with common parameters that will result in more precision. For example, stated preference data may require corrections for various response biases, while revealed preference data may require information controlling for contextual effects.…”

Section: D4 Integrating Multiple Sources Of Datamentioning

confidence: 99%

See 3 more Smart Citations

An Interdisciplinary Review of Research in Conjoint Analysis: Recent Developments and Directions for Future Research

Agarwal

DeSarbo

Malhotra

et al. 2014

Cust. Need. and Solut.

View full text Add to dashboard Cite

This review article provides reflections on the state of the art of research in conjoint analysis-where we came from, where we are, and some directions as to where we might go. We review key articles, mostly contemporary published since 2000, but some classic, drawn from the major marketing as well as various interdisciplinary academic journals to highlight important areas related to conjoint analysis research and identify more recent developments in this area. We develop an organizing framework that attempts to integrate various threads of research in conjoint methods and models. Our goal is to (a) emphasize the major developments in recent years, (b) evaluate these developments, and (c) to identify several potential directions for future research.

show abstract

Section: Suggested Directions For Future Researchmentioning

confidence: 99%

Section: A2 Compensatory Versus Noncompensatory Processesmentioning

confidence: 99%

Section: A2 Compensatory Versus Noncompensatory Processesmentioning

confidence: 99%

Section: D4 Integrating Multiple Sources Of Datamentioning

confidence: 99%

See 2 more Smart Citations

An Interdisciplinary Review of Research in Conjoint Analysis: Recent Developments and Directions for Future Research

Agarwal

DeSarbo

Malhotra

et al. 2014

Cust. Need. and Solut.

View full text Add to dashboard Cite

show abstract

“…Using estimates from a standard conjoint model together with either a ranking of all available products or top choice 9 of each consumer, they modify the standard conjoint weights to produce new weights that are consistent with the ranking over all products. [36] urge that more research is needed in order to incorporate unobserved heterogeneity, including context dependence, into choice models.…”

Section: Hypothesismentioning

confidence: 99%

A Methodology to Support Product-Differentiation Decisions

Ramdas

Zhylyevskyy

Moore

2010

IEEE Trans. Eng. Manage.

View full text Add to dashboard Cite

Choosing the right set of new products to offer is a key driver of profitability. New products often share some design attributes with existing products, thus, firms need to decide which attributes to keep common and which to differentiate. We propose and empirically implement a new methodology that can help managers to navigate the complex decision of where to focus differentiation, using "looks-like" prototypes that typically become available in the later stages of the product-development process. Our methodology complements early stage product-positioning methods, such as conjoint analysis and perceptual mapping. It also offers a way to estimate the impact of context dependence on choice. Finally, our methodology provides a way to test empirically whether perceptual mapping based on pairwise similarity judgments is appropriate for a product category. Using data obtained from a major wristwatch manufacturer, we are able to suggest guidelines on how to differentiate the firm's offerings and estimate the magnitude of context dependent effects. We also find that for wristwatches, attributes that drive perceptions differ from those that drive choice. Overall, our approach can help avoid falling into the trap of focusing variety on attributes that are costly to differentiate and have little impact on choice.Keywords product differentiation, product similarity, consumer choice, "Looks like" prototype, context dependence, conjoint analysis, perceptual mapping Choosing the right set of new products to offer is a key driver of pro tability. New products often share some design attributes with existing products, so rms need to decide which attributes to keep common, and which to differentiate. We propose and empirically implement a new methodology that can help managers navigate the complex decision of where to focus differentiation, using "looks like" prototypes that typically become available in the later stages of the product development process.Our methodology complements early stage product positioning methods such as conjoint analysis and perceptual mapping. It also offers a way to estimate the impact of context dependence on choice.Finally, our methodology provides a way to test empirically whether perceptual mapping based on pairwise similarity judgments is appropriate for a product category. Using data obtained from a major wristwatch manufacturer, we are able to suggest guidelines on how to differentiate the rm's offerings, and estimate the magnitude of context dependent effects. We also nd that for wristwatches, attributes that drive perceptions differ from those that drive choice. Overall, our approach can help avoid falling into the trap of focusing variety on attributes that are costly to differentiate and have little impact on choice.

show abstract

Modeling the bullying prevention program design recommendations of students from grades five to eight: a discrete choice conjoint experiment

Cunningham

Vaillancourt

Cunningham

et al. 2011

Aggressive Behavior

View full text Add to dashboard Cite

We used a discrete choice conjoint experiment to model the bullying prevention recommendations of 845 students from grades 5 to 8 (aged 9-14). Students made choices between experimentally varied combinations of 14 four-level prevention program attributes. Latent class analysis yielded three segments. The high impact segment (27.1%) recommended uniforms, mandatory recess activities, four playground supervisors, surveillance cameras, and 4-day suspensions when students bully. The moderate impact segment (49.5%) recommended discretionary uniforms and recess activities, four playground supervisors, and 3-day suspensions. Involvement as a bully or bully-victim was associated with membership in a low impact segment (23.4%) that rejected uniforms and surveillance cameras. They recommended fewer anti-bullying activities, discretionary recess activities, fewer playground supervisors, and the 2-day suspensions. Simulations predicted most students would recommend a program maximizing student involvement combining prevention with moderate consequences. The simulated introduction of mandatory uniforms, surveillance cameras, and long suspensions reduced overall support for a comprehensive program, particularly among students involved as bullies or bully-victims.

show abstract

Adjusting Choice Models to Better Predict Market Behavior

Cited by 68 publications

References 27 publications

An Interdisciplinary Review of Research in Conjoint Analysis: Recent Developments and Directions for Future Research

An Interdisciplinary Review of Research in Conjoint Analysis: Recent Developments and Directions for Future Research

A Methodology to Support Product-Differentiation Decisions

Modeling the bullying prevention program design recommendations of students from grades five to eight: a discrete choice conjoint experiment

Contact Info

Product

Resources

About