Applying the generalized-moments estimation approach to spatial problems involving microlevel data

• 成果类型: Article
• 署名作者: Bell, KP; Bockstael, NE
• 署名单位: University of Washington; University of Washington Seattle; University System of Maryland; University of Maryland College Park
• 刊物名称: REVIEW OF ECONOMICS AND STATISTICS
• ISSN/ISSBN: 0034-6535
• DOI: 10.1162/003465300558641
• 发表日期: 2000-02
• 页码: 72-82
• 关键词: models

摘要

The application of spatial econometrics techniques to microlevel data of firms or households is problematic because of potentially large sample sizes and more-complicated spatial weight matrices. This paper provides the first application to actual household-level data of a new generalized-moments (GM) estimation technique developed by Kelejian and Prucha. The results based on this method, which is computationally feasible for any size data set, track those generated from the more conventional maximum-likelihood approach. The GM approach is shown to have the added advantage of easily allowing estimation of a more flexible functional form for the spatial weight matrix.