We study dynamic panel data models where the long run outcome for a particular crosssection is affected by a weighted average of the outcomes in the other cross-sections. We show that imposing such a structure implies several cointegrating relationships that are nonlinear in the coefficients to...

This paper studies the spatial random effects and spatial fixed effects model. The model includes a Cliff and Ord type spatial lag of the dependent variable as well as a spatially lagged one-way error component structure, accounting for both heterogeneity and spatial correlation across units. We...

I consider a panel vector-autoregressive model with cross-sectional dependence of the disturbances characterized by a spatial autoregressive process. I propose a three-step estimation procedure. Its first step is an instrumental variable estimation that ignores the spatial correlation. In the...

We test a New Economic Geography (NEG) model for U.S. counties, employing a new strategy that allows us to bring the full NEG model to the data, and to assess selected elements of this model separately. We find no empirical support for the full NEG model. Regional wages in the U.S. do not...

I consider a panel vector autoregressive (panel VAR) model with cross sectional dependence of the model disturbances that can be characterized by a first order spatial autoregressive process. I derive asymptotic properties of a constrained maximum likelihood estimator that uses a consistent...

I illustrate the importance of choosing the correct space in empirical applications of spatial econometric models. I consider different spatial weighting matrices in an SAR(1) model -- contiguity matrix, distance based matrix and their variants adjusted for size of each observation. I show...

We estimate a model of international technological spillovers that allows for both international and inter-sectoral technology transfer, as well as international and intersectoral synergies in research and development (R&D). Furthermore we allow for a dynamic interaction in explaining total...

We propose to test for spatial correlation of the disturbances using estimated residuals of the within estimator. We derive asymptotic properties of the test and present simulation evidence to show that it also works well in finite samples.