title:         Spatial Econometrics and Political Science
authors:       David Darmofal
entrydate:     2006-01-10 22:59:14
keywords:      Spatial econometrics, Galton's problem, spatial autocorrelation
abstract:      Many theories in political science predict the spatial clustering of similar behaviors among neighboring units of observation. This spatial autocorrelation poses implications for both inference and modeling that are distinct from the more familiar serial dependence in time series analysis. In this paper, I examine how political scientists can diagnose and model the spatial dependence that our theories predict. This diagnosis and modeling entails three simple sequential steps. First, univariate spatial autocorrelation is diagnosed via global and local measures of spatial autocorrelation. Next, diagnostics are applied to a model with covariates to determine whether any spatial dependence diagnosed in the first step persists after the behavior has been modeled. If it does, the researcher simply chooses the spatial econometric specification indicated by the diagnostics. I present Monte Carlo results that demonstrate the importance of diagnosing and modeling spatial dependence in our data. I conclude by discussing how researchers can easily apply spatial econometric models in their research.

http://polmeth.wustl.edu/retrieve.php?id=575

**********************************************************
             Political Methodology E-Mail List
        Editor: Karen Long Jusko <[log in to unmask]>
**********************************************************
        Send messages to [log in to unmask]
  To join the list, cancel your subscription, or modify
           your subscription settings visit:

          http://polmeth.wustl.edu/polmeth.php

**********************************************************