Spatial Patterns and Irregularities of the electoral data: general elections in Canada

Dissertation submitted in partial fulfillment of the requirements for the Degree of Master of Science in Geospatial Technologies.

Democratic elections are one of the most important social phenomena of the last centuries. Countries which publish elections results on the polling station level provide a valuable source of data for different groups of scientists like geographers and statisticians. In this work, we combined geographical and statistical analysis, pursuing a goal of defining the spatial patterns and irregularities of the electoral data. From theoretical point of view, it will help to find out if the electoral behavior has any spatial dependency. From practical perspective, it can give a new insight about the electoral fraud detection. We have applied a set of statistical methods to estimate the distribution and variability of the electoral behavior in space and time for different geographic units. Canada was selected as a study area because it is an old democracy where the elections are considered being fair, and all the necessary data are available.