On Accommodating Spatial Interactions in a Generalized Heterogeneous Data Model (GHDM) of Mixed Types of Dependent Variables

The authors develop an econometric framework for incorporating spatial dependence in integrated model systems of latent variables and multidimensional mixed data outcomes. The framework combines Bhat’s Generalized Heterogeneous Data Model (GHDM) with a spatial formulation to introduce spatial dependencies through latent constructs. Monte Carlo simulation experiments on synthetic data demonstrate the efficacy of the maximum approximate composite marginal likelihood (MACML) approach in recovering parameters from spatially dependent datasets, as accurately and precisely as that from aspatial data (without spatial dependency). The results also suggest that ignoring spatial dependency can lead to a substantial loss in the accuracy and efficiency of parameter estimation and in overall data fit.

Language

  • English

Media Info

  • Media Type: Digital/other
  • Features: References; Tables;
  • Pagination: 32p

Subject/Index Terms

Filing Info

  • Accession Number: 01626755
  • Record Type: Publication
  • Report/Paper Numbers: D-STOP/2016/120
  • Contract Numbers: DTRT13-G-UTC58
  • Files: UTC, TRIS, ATRI, USDOT
  • Created Date: Feb 27 2017 9:26AM