Spatial Regression of the Gross County Product of Kenya on Induced Latent Variables

Abstract

Since the re-organization of the local boundaries in Kenya from provinces to counties in 2013, there had been few studies carried out to measure regional economic progress. The role of geographical analysis in economic development had been of less concern in Kenya. Investigating the spatial dependence of the Gross County Product GCP of Kenya on latent variables was important as it solved the error of model misspecification and in the relationship could have proved the spill-over effect of the Kenyan economy at the county levels. This cross-sectional study identified the common factors among the economic indicators through factor analysis and the economic development of the country by use of thematic maps. The Kenya National Bureau of Statistics (KNBS) published and publicized the 2019 geocoded dataset as a Kenyan economic survey report for that year which consisted of 47 Kenyan counties and 18 county economic indicators which were used in this study. The Local Indicator of Spatial Association (LISA) (Moran I test) for spatial clustering and the Maximum Likelihood Estimation (MLE) method was employed to obtain the parameter estimates of the spatial relationship which were important for policy making among various economic stakeholders in the country. The Lagrange Multiplier (LM) Test together with the spatial Hausman test suggested an error model fit, lags being significant, or endogeneity. Meanwhile, the likelihood ratio test considered a restricted spatial model more suitable than the nested model. The ArcGIS (version 10.7.1) and R (version 4.3.0) software were used for spatial analysis. The Spatial error model (SEM) results gave out a suitable equation that revealed the relationship between the GCP and the county indicators. This produced a benchmark for explaining geocoded datasets for monitoring the economic pattern of Kenya and correct how the 6 economic blocs were classified geographically while highlighting the drawbacks in the achievement of Kenya's development programs like Vision 2030 and Sustainable Development Goals