The paper presents a three-stage iterative procedure for building space-time autoregressive integrated moving average (STARIMA) models.
The model-building is illustrated with the spatial data base for tractor ownership. The paper discusses and compares the resulting STARIMA model and models previously postulated (Casetti and Semple, 1969, and Cliff and Ord, 1975), with particular focus on the differences in model form, assumptions inherent in the modeling, and the descriptive capability of the resulting models. Tables, formulas, and 15 references are included. (Author summary modified)
Downloads
Similar Publications
- Predictors of physical assault victimization: Findings from the National Survey of Adolescents
- Do Prison Administrative and Survey Data Sources Tell the Same Story? A Multitrait, Multimethod Examination With Application to Gangs
- The Nature of Rater Effects and Differences in Multilevel MTMM Latent Variable Models