Application of Spatial Econometrics Methods in the Analysis of WLAN Performance

This paper presents the spatial econometric modeling to performance prediction analysis of high-density client environments in higher education. According to our knowledge, these methods were not yet used in such analysis. Particular attention was devoted to SAR (Spatial Autoregressive Model) and SEM (Spatial Error Model) models, and their comparison with a classical non-spatial regression model. We have created models for two neighbor matrices to take into account different looks at distance definition in a 3D environment. The models were compared how well they predict the number of logged users which is considered as the WLAN performance index.