Data Aggregation and Information Loss

Analysts often use a single average or otherwise aggregated price series to represent several geographic or product markets even when disaggregate data are available. We hypothesize that such an approach may not be appropriate under some circumstances, such as when only long-term relationships hold among price series or when homogeneous but relatively perishable products are considered. This question is of particular relevance in agriculture because of seasonality in production and harvest across various production regions, and the effect of changes in demand as substitute crops become available. We analyze this question in the context of fresh strawberry production. We find that in the case of the strawberry market, aggregate series are appropriate for long-term decision analysis, but some information loss occurs when conducting short-term decision analysis.


Issue Date:
2007
Publication Type:
Conference Paper/ Presentation
PURL Identifier:
http://purl.umn.edu/9843
Total Pages:
23
Series Statement:
Selected Paper 174289




 Record created 2017-04-01, last modified 2017-08-23

Fulltext:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)