Characterising spatial variance
Much of the research in spatial analysis focuses on covariance structures in space and time. We are interested in the investigation of spatial structures in the variance. Although the latter is related to covariance, it reflects exogenous influences rather than cluster or repulsion effects. Our focus on variance is motivated by the study of heterogeneous data sets as extracted from social media, blogs, or other types of Big Data sources.
Data from everyday life, and especially those generated by ordinary people themselves, are complex. Such data represent parts of the life worlds of individuals including their perceptions, conceptions of the world, opinions, and many other aspects. This diversity is also reflected in the spatial and temporal structure of this type of data. However, existing methods for assessing spatial heterogeneity are not sufficiently suitable for characterising these complex, unsystematic, and mixed data types. We are therefore working on novel methods for a better understanding of Big Data sources that are not characterised by spatial partitioning but by spatial superimpositions. The methodological approaches used include measures of spatial heterogeneity, spatial filtering-based approaches, among others. In this way, we contribute to a better understanding of the organisation of human everyday life.
Publications
Bucher, D., Martin, H., Jonietz, D., Raubal, M. and Westerholt, R. (2020): Estimation of Moran’s I in the Context of Uncertain Mobile Sensor Measurements. 11th International Conference on Geographic Information Science (GIScience 2021) - Part I, Poznan, Poland. DOI: 10.4230/LIPIcs.GIScience.2021.I.2.
Westerholt, R., Resch, B., Mocnik, F.-B., and Hoffmeister, D. (2018): A statistical test on the local effects of spatially structured variance. International Journal of Geographical Information Science, 32 (3), 571–600. DOI: 10.1080/13658816.2017.1402914.
Westerholt, R. (2018): The impact of the spatial superimposition of point based statistical configurations on assessing spatial autocorrelation. In: Proceedings of the 21st AGILE Conference on Geographic Information Science, Lund, Sweden.
Westerholt, R. (2017): Topological and scale-related issues in Twitter analyses through superimposed forms of spatial heterogeneity. Annual Meeting of the American Association of Geographers 2017, Boston, MA.
Westerholt, R., Steiger, E., Resch, B. and Zipf, A. (2016): Abundant Topological Outliers in Social Media Data and Their Effect on Spatial Analysis. PLOS ONE, 11 (9), e0162360. DOI: 10.1371/journal.pone.0162360.
