Spatial parameter variation by Orthogonal Trend Surface Expansions: An application to the analysis of welfare program participation rates

This paper describes Orthogonal Trend Surface Expansions (OTSEs), a technique for investigating the spatial variation of a model's parameters. OTSEs implement in spatial contexts the Expansion Method's approach to the study of parametric stability/drift. Here OTSEs are used to test for parameter variation in a model of participation in Aid to Families with Dependent Children (AFDC), a large U.S. welfare program.