Urban and regional distinctions for aggregating time series data |
| |
Authors: | Harvey Cutler Scott England Stephan Weiler |
| |
Affiliation: | Colorado State University, Department of Economics, Fort Collins, CO 80523–1771, USA (e-mail: , ); Colorado Public Utilities Commission, Department of Regulatory Agencies, 1560 Broadway, Denver, CO 80202, USA (e-mail: ) |
| |
Abstract: | Abstract. This article argues that using either the SIC or NAICS one-digit classifications as a method of aggregating two- and three-digit time series data can ignore important regional characteristics. We present a pairwise cointegration approach of aggregation where the aggregated sectors can vary widely across regions. By systematically constructing region-specific sectors from more detailed industries, we find that the level of agglomeration across rural and urban areas can affect the composition and number of local sectors in a region. We use the results pointing to rural/urban geographic distinctiveness to further consider the Carlino and Defina (1998, 1999 ) finding that monetary policy has disparate effects across regions in the U.S. |
| |
Keywords: | E52 R15 R51 C22 C43 |
|
|