What Are High-Quality Statistics Worth?

• Activity Number: 23 - What Are High-Quality Statistics Worth?
• Type: Invited
• Date/Time: Monday, August 3, 2020 : 10:00 AM to 11:50 AM
• Sponsor: Business and Economic Statistics Section
• Author(s): John Eltinge* and John Fernald* and Erica Groshen* and Maurine Haver* and Jack Kleinhenz*
• Companies: Census Bureau and Federal Reserve Bank of San Francisco and INSEAD and Cornell University and former Commissioner of the Bureau of Labor Statistics and Haver Analytics and Kleinhenz & Associates, LTD and National Retailers Association
• Keywords: multiple data sources; public goods; use value and option value; official statistics; stakeholder value; communication

Abstract

Government statistical agencies have a mission to provide high-quality information on a sustainable and cost-effective basis. Practical work to fulfill this mission with limited resources will always require agencies to address two complementary questions about the relationship between data quality and stakeholder value.

1. What is the best way to make decisions about trade-offs among competing dimensions of data quality, including accuracy, relevance, timeliness and granularity of published statistics; and accessibility, discoverability, comparability, and interpretability of specific data products. There is extensive literature on the definition and measurement of these dimensions. However, we know far less about how changes in one dimension of quality affect the value delivered to stakeholders, and how these translations depend on specific contexts.

2. How can agencies communicate the connection between data quality and stakeholder value in concrete ways that will resonate with decision-makers and the public? Here again, contextual factors warrant in-depth study. This session will explore these two questions through a set of presentations, followed by a structured discussion.