Working Paper: NBER ID: w25465
Authors: Gabriel Ehrlich; John C. Haltiwanger; Ron S. Jarmin; David Johnson; Matthew D. Shapiro
Abstract: Key macro indicators such as output, productivity, and inflation are based on a complex system across multiple statistical agencies using different samples and different levels of aggregation. The Census Bureau collects nominal sales, the Bureau of Labor Statistics collects prices, and the Bureau of Economic Analysis constructs nominal and real GDP using these data and other sources. The price and quantity data are integrated at a high level of aggregation. This paper explores alternative methods for re-engineering key national output and price indices using item-level data. Such re-engineering offers the promise of greatly improved key economic indicators along many dimensions.
Keywords: Economic Measurement; GDP; Inflation; Item-Level Data
JEL Codes: D12; E01; E20; E31
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| integration of item-level transaction data (L81) | improvement in measurement of key economic indicators (E01) |
| digitized data from sources like scanner data (Y10) | more accurate nominal revenue and price indices (E30) |
| adopting a more integrated approach using item-level data (C81) | better estimates of real output and productivity (E23) |
| item-level data (Y10) | generation of macro indicators in a consistent manner with underlying micro data (E10) |