Central Limit Theorems and Uniform Laws of Large Numbers for Arrays of Random Fields.

摘要: Over the last decades, spatial-interaction models have been increasingly used in economics. However, development of a sufficiently general asymptotic theory for nonlinear spatial has hampered by lack relevant central limit theorems (CLTs), uniform laws large numbers (ULLNs) and pointwise (LLNs). These form essential building blocks towards developing M-estimators, including maximum likelihood generalized method moments estimators. The paper establishes CLT, ULLN, LLN processes or random fields that should be applicable to broad range data processes.