Third, we used spatial regression models to evaluate the departure from the monocentric city model for both cities. Nested square windows represent the scale of analysis i.
Both indices accounted for the dimension of connectivity. Because we also evaluated scale sensitivity of urbanization measures, we calculated all variables at three different scales: 0.
As in the cluster analysis, percentage of water for Vienna and percentage of forest for Amsterdam were excluded, because of the small proportion of landscape covered.
We also calculated an index of sampling adequacy using Kaiser—Meyer—Olkin which produces a value between 0 and 1, with a cut-off value of 0. The demographic variables and road network density were calculated using ArcGIS v. Study regions for the current research, Bangalore and Ahmadabad are one of the fastest developing urban centers of India.