Hierarchical Effects for Russian Regions: Spatial Modeling

This study examined spatial effects for two forms of data aggregation — the federal district and the macroregion. The research question is to find the most effective form of territorial organization. To answer the question posed, econometric analysis methods were used, which included the calculation of the Moran index to confirm the presence of spatial effects for the regions of Russia, the construction of two types of weighting matrics: boundary matrices and inverse distance matrices, as well as the construction of spatially econometric models for panel data with hierarchical structure. For each data type, a static SAR model for panel data was constructed, which was estimated using the maximum likelihood method. The calculations were carried out both for all regions of Russia, and separately for federal districts and macroregions. The study was conducted according to data describing the socio-economic development of the regions of Russia from 2005 to 2017 for 73 subjects of the Russian Federation. Data collected from the official website of the Federal State Statistics Service. Data analysis was carried out using the software resources of the R package and its development environment RStudio, and the statistical package STATA. According to the results of the study, the hypothesis of the presence of spatial effects for all regions was confirmed. It is impossible to say unequivocally how the form of organization of subjects is most effective.