610.5
Mapping As a Tool of Improving Cluster Analysis Results

Friday, 20 July 2018: 09:18
Location: 203D (MTCC NORTH BUILDING)
Oral Presentation
Shamil FARAKHUTDINOV, Industrial University of Tyumen, Russia
Cluster analysis is widely used in sociological research. One of the crucial issues for the researcher is an optimal number of clusters. On the one hand, he should not fall into excessive describing; on the other hand, the number must be enough to reveal the whole range of possible elements’ groups to reach the research goals. The studies, where research objects have spatial localization, the use of mapping technics and spatial analysis can be rather helpful for determining an optimal number of clusters. This idea is based on our research experience, dedicated to rural municipalities cluster analysis.

The polarization process of the Russian rural territories continues and lasts more than 20 years. It is a consequence of the USSR collapse. Studying these processes we have collected empirical data and chosen 7 key quantitative markers. Then, a hierarchical cluster analysis was conducted with SPSS. The case was in one of the West Siberian regions.

It was noticed that socio-economic development of rural settlements was determined by their geographical position. Natural and climate conditions, soil fertility, degree of remoteness from towns and major roads, proximity to oil and gas pipeline stations, agricultural enterprises, administrative borders and national enclaves are the "magnets" with different force of gravity or repulsion. We used QGIS to put these “magnets” on the map to define their strength as factors, distinguishing clusters. Subsequent analysis allowed us to reveal general trends and latent mechanisms of rural space polarization, discard minor factors, enlarge and rebuild our cluster model.

Using mapping technics and spatial analysis is a good way to visualize data to ease its perception. Also, it is a research tool to identify new social phenomena. If the research object is localized in space, visual information allows complementing analysis with factors, difficult to reveal and describe both quantitatively and qualitatively.