Spatial data analysis 1600-SZD-WM-SDA
Classes deal with the applied methods of statistical and econometric analysis of spatial data (regional, point, grid data). The aim of the course is to learn how to quantify location, co-location and distance in modeling phenomena of diffusion, agglomeration and location density, specialization, geographical rent, absolute and relative location, spatial interaction, spatial autocorrelation, spatial sorting and heterogeneity. The latest methods of spatial analysis will be presented, with a strong emphasis on the applied approach. All modeling problems will be presented and solved in the R software. Examples of problems will concern socio-economic phenomena, such as economic policy, social processes in the geographical space, location of companies.
Teaching methods applied:
- lectures on the issues discussed
- solving research problems - planning the details of quantitative analysis
- programming in R (loading data, writing codes needed for the study)
- interpretation of results and its confrontation with the subject literature (from a quantitative and thematic perspective)
Topics:
- spatial statistics for regional (areal) data, study of spatial distributions (Moran I, Getis-Ord, LOSH, LISA, join-count, DBSCAN), statistics for data in a grid
- econometric modeling of spatial dependency (with a use of a spatial weight matrix) - single-period, dynamic and panel models - model and variable selection, estimation, testing, forecasting, missing data, spatial interactions, models on area and point data (including GNS, SDM, SDEM, SAC, SEM, SAR, SLX, GWR)
- big data and machine learning challenges in relation to spatial data - point data clustering, spatial PCA, bootstrapped regression (including sampling and replication problems, interpretation of results)
Type of course
Course coordinators
Learning outcomes
- PhD student knows and understands how to use quantitative spatial methods
- PhD student knows and understands the basic principles of knowledge transfer to the economic and social sphere as well as commercialization of the results of scientific activities and know-how related to these results.
- PhD student is able to plan and conduct research in order to find answers to substituted research questions of a spatial nature
- PhD student understands the issues of spatial phenomena, including location, co-location and distance in modeling phenomena of diffusion, agglomeration and location density, specialization, geographical rent, absolute and relative location, spatial interaction, spatial autocorrelation, spatial sorting and heterogeneity.
- PhD student is able to use knowledge from various fields of science or the field of art to creatively identify, formulate and innovatively solve complex problems or perform research tasks
- PhD student is able to define the purpose and subject of scientific research, formulate a research hypothesis
- PhD student to develop research methods, techniques and tools, apply them creatively and infer based on the results of scientific research.
Assessment criteria
Partial grades are given for the review and paper. The final grade is the average of partial grades (weights of 50%).
- description of requirements related to participation in classes, including the permitted number of explained absences;
Attendance is obligatory. For each absence, PhD student writes an essay ca. 2 pages A4 (normalized text) about the topics covered in class (topics and questions presented by the teacher). The number of absences cannot exceed 50% of classes.
- principles for passing the classes and the subject (including resit session);
The credit includes two components:
a) Written review of the article assigned by the teacher
b) Paper on a topic agreed with the teacher (own research, replication / extension of existing research, application of existing solutions to new problems)
The component of the credit presented in the basic session can be recognized in the retake session.
- methods for the verification of learning outcomes;
Implementation of the elements of credit - a review and own research allows to examine the degree of perception of assumed learning outcomes
Bibliography
Kopczewska K (eds.) (2020), Applied Spatial Statistics and Econometrics: Data Analysis in R, Routledge
Scientific papers (in English) selected by interests and needs of PhD students
Additional information
Additional information (registration calendar, class conductors, localization and schedules of classes), might be available in the USOSweb system: