Activity Number:
|
73
- Data Driven Digital and Social Media Marketing
|
Type:
|
Contributed
|
Date/Time:
|
Sunday, July 29, 2018 : 4:00 PM to 5:50 PM
|
Sponsor:
|
Section on Statistics in Marketing
|
Abstract #329289
|
Presentation
|
Title:
|
Build-Your-Own Dashboards for Metric Choice
|
Author(s):
|
Peter Lenk* and Ofer Mintz and Yakov Bart and David Reibstein
|
Companies:
|
University of Michigan and University of Sydney and Northeastern University and University of Pennsylvania
|
Keywords:
|
Metrics;
Marketing;
Conjoint;
Multivariate Probit;
Ordinal Probit;
Hierarchical Bayes
|
Abstract:
|
We adapt build-your-own methodology to study how managers make tradeoffs when constructing dashboards for different marketing decisions. The subjects select metrics to create dashboards for managing marketing decisions. After selecting the metrics, the subjects rank the selected metrics for importance in managing the marketing decision and for reporting the results to upper management. We use a multivariate probit model for the selection of metrics and ordinal probit models for ranking the metrics. We control for selection effects by correlating the error terms of the models and using exclusion restrictions. Our results indicate that mangers tend to select marketing metrics that have a better fit to the decision. Second, managers tend to select complementary metrics instead of loading-up on near substitutes. Third, there is some indication that metrics vary in their importance for managing the project and reporting the result.
|
Authors who are presenting talks have a * after their name.