Estimation of Random-Coefficient Demand Models: Two Empiricists' Perspective

Knittel, Christopher R.; Μεταξόγλου, Κωνσταντίνος

doi:10.1162/rest_a_00394

Cited by 122 publications

(78 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here, the weighting matrix Φ is a consistent estimate of E[Z ξ(θ)ξ(θ) Z], and is obtained employing the usual two-stage procedure (see Nevo 2000 for more details). Finally, as noted by Knittel and Metaxoglou (2014), the estimation procedure is subject to variability depending on the optimization algorithms and initial values considered. Similarly, Dube et al (2012) note the dangers of using loose tolerance levels in the estimation procedure.…”

Section: Estimationmentioning

confidence: 99%

Service Competition and Product Quality in the U.S. Automobile Industry

2016

View full text Add to dashboard Cite

We study the impact of service attributes (warranty length, after-sales service quality) on consumer demand in the U.S. automobile industry, examining the presence of complementarities/substitution between service attributes and product quality. Our results estimate a median willingness to pay for one year of a warranty of approximately $850, which is equivalent to 3.1% of the median vehicle price in our sample. We find that, for a car with median characteristics, the effect on consumer utility of a 1% price decrease is equivalent, all else being equal, to increasing product quality by 2.2%, and is in turn equivalent to increasing the warranty length by 8%. Our results also indicate that service attributes play a compensatory role with respect to product quality; i.e., the impact of warranty length and service quality on demand increases when product quality decreases. Conversely, both service metrics are complementary with respect to demand; i.e., the better the service quality, the higher the marginal effect of longer warranties. Our results thus imply that, in our period of analysis, warranties played a more important role for American firms than for foreign firms, consistent with the fact that American manufacturers exhibited lower product quality and higher service quality than nonAmerican firms. We study the impact of service attributes (warranty length, after-sales service quality) on consumer demand in the U.S. automobile industry, examining the presence of complementarities/substitution between service attributes and product quality. Our results estimate a median willingness to pay for one year of warranty of about $850, which is equivalent to 3.1% of the median vehicle price in our sample. Wend that, for a car with median characteristics, the effect on consumer utility of a 1% price decrease is equivalent, all else being equal, to increasing product quality by 2.2%, and is in turn equivalent to increasing the warranty length by 8%. Our results also indicate that service attributes play a compensatory role with respect to product quality, i.e., the impact of warranty length and service quality on demand increases when product quality decreases. Conversely, both service metrics are complementary with respect to demand, i.e., the better the service quality, the higher the marginal effect of longer warranties. Our results thus imply that, in our period of analysis, warranties played a more important role for American firms than for foreign firms, consistent with the fact that American manufacturers exhibited lower product quality and higher service quality than non-American firms. AbstractWe study the impact of service attributes (warranty length, after-sales service qual-

show abstract

Section: Estimationmentioning

confidence: 99%

Service Competition and Product Quality in the U.S. Automobile Industry

2016

View full text Add to dashboard Cite

show abstract

“…Our work complements some recent papers in which alternative estimation approaches and extensions of the standard random coefficients logit model have been proposed, including Villas-Boas and Winer (1999), Knittel and Metaxoglou (2014), Dube et al (2012), Harding and Hausman (2007), Bajari et al (2011), and Gandhi et al (2010).…”

Section: Introductionmentioning

confidence: 62%

Estimation of Random Coefficients Logit Demand Models with Interactive Fixed Effects

2017

View full text Add to dashboard Cite

JEL classification: C23 C25 Keywords:Discrete-choice demand model Interactive fixed effects Factor analysis Panel data Random utility model a b s t r a c tWe extend the Berry, Levinsohn and Pakes (BLP, 1995) random coefficients discrete-choice demand model, which underlies much recent empirical work in IO. We add interactive fixed effects in the form of a factor structure on the unobserved product characteristics. The interactive fixed effects can be arbitrarily correlated with the observed product characteristics (including price), which accommodate endogeneity and, at the same time, capture strong persistence in market shares across products and markets. We propose a two-step least squares-minimum distance (LS-MD) procedure to calculate the estimator. Our estimator is easy to compute, and Monte Carlo simulations show that it performs well. We consider an empirical illustration to US automobile demand.

show abstract

“…Our work complements some recent papers in which alternative estimation approaches and extensions of the standard random coefficients logit model have been proposed, including Villas-Boas and Winer (1999), Knittel and Metaxoglou (2014), Dube, Fox and Su (2012), Harding and Hausman (2007), Bajari, Fox, Kim and Ryan (2011), and Gandhi, Kim and Petrin (2010).…”

Section: Introductionmentioning

confidence: 62%

Estimation of random coefficients logit demand models with interactive fixed effects

Shum¹,

Moon²,

Weidner³

2014

View full text Add to dashboard Cite

We extend the Berry, Levinsohn and Pakes (BLP, 1995) random coefficients discretechoice demand model, which underlies much recent empirical work in IO. We add interactive fixed effects in the form of a factor structure on the unobserved product characteristics. The interactive fixed effects can be arbitrarily correlated with the observed product characteristics (including price), which accommodates endogeneity and, at the same time, captures strong persistence in market shares across products and markets. We propose a two step least squares-minimum distance (LS-MD) procedure to calculate the estimator. Our estimator is easy to compute, and Monte Carlo simulations show that it performs well. We consider an empirical illustration to US automobile demand.

show abstract

Estimation of Random-Coefficient Demand Models: Two Empiricists' Perspective

Cited by 122 publications

References 51 publications

Service Competition and Product Quality in the U.S. Automobile Industry

Service Competition and Product Quality in the U.S. Automobile Industry

Estimation of Random Coefficients Logit Demand Models with Interactive Fixed Effects

Estimation of random coefficients logit demand models with interactive fixed effects

Contact Info

Product

Resources

About