A probit model with structured covariance for similarity effects and source of volume calculations

Jeffrey P. Dotson, John Richard Howell, Jeff D. Brazell, Thomas Otter, Peter J. Lenk, Steve Maceachern, Greg M. Allenby

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Distributional assumptions for random utility models play an important role in relating observed product attributes to choice probabilities. Choice probabilities derived with independent errors have the property of independence of irrelevant alternatives, which often does not match observed substitution behavior and leads to inaccurate calculations of source of volume when new entrants are introduced. In this article, the authors parameterize the covariance matrix for a probit model so that similar brands in the preference space have higher correlation than dissimilar brands, resulting in higher rates of substitution. They find across multiple data sets that similarity based on overall utility, not just attributes, defines products as similar with heightened rates of substitution. The proposed model results in better in-sample and predictive fits to the data and more realistic measures of substitution for a new product introduction.

Original languageEnglish (US)
Pages (from-to)35-47
Number of pages13
JournalJournal of Marketing Research
Volume55
Issue number1
DOIs
StatePublished - Feb 1 2018

Fingerprint

Probit model
Substitution
Product attributes
New product introduction
Covariance matrix
Random utility model
Independence of irrelevant alternatives
New entrants

All Science Journal Classification (ASJC) codes

  • Business and International Management
  • Economics and Econometrics
  • Marketing

Cite this

Dotson, Jeffrey P. ; Howell, John Richard ; Brazell, Jeff D. ; Otter, Thomas ; Lenk, Peter J. ; Maceachern, Steve ; Allenby, Greg M. / A probit model with structured covariance for similarity effects and source of volume calculations. In: Journal of Marketing Research. 2018 ; Vol. 55, No. 1. pp. 35-47.
@article{744975a897a7492aa241849c4306ea0d,
title = "A probit model with structured covariance for similarity effects and source of volume calculations",
abstract = "Distributional assumptions for random utility models play an important role in relating observed product attributes to choice probabilities. Choice probabilities derived with independent errors have the property of independence of irrelevant alternatives, which often does not match observed substitution behavior and leads to inaccurate calculations of source of volume when new entrants are introduced. In this article, the authors parameterize the covariance matrix for a probit model so that similar brands in the preference space have higher correlation than dissimilar brands, resulting in higher rates of substitution. They find across multiple data sets that similarity based on overall utility, not just attributes, defines products as similar with heightened rates of substitution. The proposed model results in better in-sample and predictive fits to the data and more realistic measures of substitution for a new product introduction.",
author = "Dotson, {Jeffrey P.} and Howell, {John Richard} and Brazell, {Jeff D.} and Thomas Otter and Lenk, {Peter J.} and Steve Maceachern and Allenby, {Greg M.}",
year = "2018",
month = "2",
day = "1",
doi = "10.1509/jmr.13.0240",
language = "English (US)",
volume = "55",
pages = "35--47",
journal = "Journal of Marketing Research",
issn = "0022-2437",
publisher = "American Marketing Association",
number = "1",

}

A probit model with structured covariance for similarity effects and source of volume calculations. / Dotson, Jeffrey P.; Howell, John Richard; Brazell, Jeff D.; Otter, Thomas; Lenk, Peter J.; Maceachern, Steve; Allenby, Greg M.

In: Journal of Marketing Research, Vol. 55, No. 1, 01.02.2018, p. 35-47.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A probit model with structured covariance for similarity effects and source of volume calculations

AU - Dotson, Jeffrey P.

AU - Howell, John Richard

AU - Brazell, Jeff D.

AU - Otter, Thomas

AU - Lenk, Peter J.

AU - Maceachern, Steve

AU - Allenby, Greg M.

PY - 2018/2/1

Y1 - 2018/2/1

N2 - Distributional assumptions for random utility models play an important role in relating observed product attributes to choice probabilities. Choice probabilities derived with independent errors have the property of independence of irrelevant alternatives, which often does not match observed substitution behavior and leads to inaccurate calculations of source of volume when new entrants are introduced. In this article, the authors parameterize the covariance matrix for a probit model so that similar brands in the preference space have higher correlation than dissimilar brands, resulting in higher rates of substitution. They find across multiple data sets that similarity based on overall utility, not just attributes, defines products as similar with heightened rates of substitution. The proposed model results in better in-sample and predictive fits to the data and more realistic measures of substitution for a new product introduction.

AB - Distributional assumptions for random utility models play an important role in relating observed product attributes to choice probabilities. Choice probabilities derived with independent errors have the property of independence of irrelevant alternatives, which often does not match observed substitution behavior and leads to inaccurate calculations of source of volume when new entrants are introduced. In this article, the authors parameterize the covariance matrix for a probit model so that similar brands in the preference space have higher correlation than dissimilar brands, resulting in higher rates of substitution. They find across multiple data sets that similarity based on overall utility, not just attributes, defines products as similar with heightened rates of substitution. The proposed model results in better in-sample and predictive fits to the data and more realistic measures of substitution for a new product introduction.

UR - http://www.scopus.com/inward/record.url?scp=85049525866&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85049525866&partnerID=8YFLogxK

U2 - 10.1509/jmr.13.0240

DO - 10.1509/jmr.13.0240

M3 - Article

VL - 55

SP - 35

EP - 47

JO - Journal of Marketing Research

JF - Journal of Marketing Research

SN - 0022-2437

IS - 1

ER -