Dynamic Quality Ladder Model Predictions in Nonrandom Holdout Samples

56 Pages Posted: 25 Jul 2014 Last revised: 20 Jan 2017

Linli Xu

University of Minnesota - Twin Cities - Carlson School of Management

Kenneth C. Wilbur

University of California, San Diego (UCSD) - Rady School of Management

Jorge M. Silva-Risso

University of California, Riverside (UCR) - A. Gary Anderson Graduate School of Management

Date Written: December 7, 2016

Abstract

In light of recent calls for further validation of structural models, this paper evaluates the popular Dynamic Quality Ladder model of the Ericson and Pakes (1995) empirical framework using the nonrandom holdout approach of Keane and Wolpin (2007). The model is used to predict data following a regime shift — i.e., a change in the environment that produced the estimation data. The prediction performance is evaluated relative to a benchmark Vector Autoregression model across three automotive categories and multiple prediction horizons. Whereas the VAR model performs better in all scenarios in the Compact Car category, the DQL model tends to perform better on multiple-year horizons in both the Midsize Car and Fullsize Pickup categories. A supplementary data analysis suggests that DQL model performance in the non-random holdout prediction task is better in categories that are more affected by the regime shift, helping to validate the usefulness of the dynamic structural model for making predictions after policy changes.

Keywords: Product Quality, Dynamic Oligopoly Competition, Nonrandom Holdout Validation

Suggested Citation

Xu, Linli and Wilbur, Kenneth C. and Silva-Risso, Jorge M., Dynamic Quality Ladder Model Predictions in Nonrandom Holdout Samples (December 7, 2016). Available at SSRN: https://ssrn.com/abstract=2471237 or http://dx.doi.org/10.2139/ssrn.2471237

Linli Xu (Contact Author)

University of Minnesota - Twin Cities - Carlson School of Management ( email )

321 - 19th Avenue South
Minneapolis, MN 55455
United States

HOME PAGE: http://www.tc.umn.edu/~linlixu/

Kenneth C. Wilbur

University of California, San Diego (UCSD) - Rady School of Management ( email )

9500 Gilman Drive
Rady School of Management
La Jolla, CA 92093
United States

HOME PAGE: http://kennethcwilbur.com

Jorge M. Silva-Risso

University of California, Riverside (UCR) - A. Gary Anderson Graduate School of Management ( email )

Riverside, CA 92521
United States

Paper statistics

Downloads
150
Rank
159,040
Abstract Views
882