In the paper the method of data set homogeneity examination and algorithm of set division into homogeneous subsets (in quality sense) are presented and its application for modeling regional structure is demonstrated. The essential element of the method is criterionfor testing data set homogeneity hypothesis. The criterionfunction has a form of statistics U, which has the i distribution. The method consists in iterative partition of non homogeneous set into two parts. If number of this division increases, than the process of successive partitions can lead to the existence of statistical unstable boundaries between adjacent homogeneous subsets. The determination of unstable intergroup boundaries and their removalfrom earlier obtained partitionfinally results in data set division into homogeneous separated subsets with stable interbounds. The presented algorithm was used for selecting the homogeneous groups of vojvodships in Poland described by a set of charakteristics. The considered data concem the year 1998, 2000, 2001.
Operational Program Digital Poland, 2014-2020, Measure 2.3: Digital accessibility and usefulness of public sector information; funds from the European Regional Development Fund and national co-financing from the state budget.
Oct 15, 2021
Feb 1, 2021