SQM: Selected quantitative methods and procedures for urban research and decision making.
Participants are organized as a research group simultaneously combining theory, methods and data analysis. Since there are no textbooks with this approach, the instructor has carefully selected readings and requested the data sets from the authors to explore five areas of spatial research. The students will replicate the readings and discuss how the information can be applied to other case studies with similar theoretical approaches. Calculations use spreadsheets (Excel), standard statistical software (i.e., SPSS or Minitab) and software for geographic information systems environments (ArcGIS 10.2—Spatial Statistics Tools—and GeoDa). No previous course or experience in the required software is necessary. Participants will become familiar with the software by using it. The course is oriented to graduate students interested in applied spatial analysis or spatial thinking. Prerequisites. A research idea, a georeferenced database and some prior exposure to basic statistics are highly desirable. Students simultaneously registered in Urban Spatial Analysis will receive the benefit of reducing the effort required to handle similar or complementary research topics and statistical procedures.
No textbook is required. Materials will be adjusted and notes will be provided by the instructor, depending on the research interest of the participants.
Read more on this approach of the course Link
Specific objectives. At the end of the course, participants will be able to:
―Address spatial problems outside their own researching interest and import methodologies from other fields of study.
―Formulate hypotheses and articulate intermediate statistical procedures to test them.
―Elaborate their own interpretations and understand those from other participants.
Outline (approach)
1. Data screening
― Skewness and tests of normality.
― Detection of univariate and multivariate outliers. BoxPlot, MAD, z, D2- Mahalanobis.
― Data transformation. Box-Cox, Z-Mad, Robust normalization box plots (Robust Normalized Boxplot).
Download readings here ; here & a ppt form here
2. Techniques for mapping and visualization of data
― Criteria to elaborate and evaluate strata: ANOVA-GVF-GADF.
― Cartograms.
― Hue of color.
Downlaod Silesia here; Heads/tails procedure here; ANOVA here; Summary of parametric & non-parametric stats (includes instructions for the midterm paper) here
3. Basic portfolio of indices of inequality
The Gini family: LQ, Hoover and Gini index here & here
Other common indices: here
4. Simple and multivariate regression with ordinary least squares (*).
― Regression, ANOVA and Dummy variables.
― Model building.
5. Spatial autocorrelation (*)
6. Spatial regression (*)
― Spatial lag
― Spatial error
7. Geographically weighted regression (*)
8. Factor Analysis (optional)
9. Cluster analysis here
(*) These topics have been skipped to include Cluster Analysis (originally scheduled as optional).
Guidelines for your final paper here
Basic bibliography (indicative)
Anselin, Luc, and Sergio J. Rey (Eds.). 2010. Perspectives on Spatial Data Analysis. Berlin: Springer- Verlag.
Brimicombe, A.J., 2000, Constructing and evaluating contextual indices using GIS: a case of primary school performance. Environment & Planning A, 32, 1909-1933.
Ebdon, David. 1985. Statistics in Geography. 2a. Ed. New York, NY.: Basil Blackwell Inc.
Fischer, Manfred M. and Arthur Getis. 2010. Handbook of Applied Spatial Analysis Software Tools, Methods and Applications. Berlin-Heidelberg: Springer-Verlag.
Fischer, Manfred M. and Peter Nijkamp (Editors). 2013. Handbook of Regional Science. Berlin Heidelberg: Springer-Verlag.
Fratesi, Ugo and Lanfranco Senn (Editors). 2009. Growth and Innovation of Competitive Regions. The Role of Internal and External Connections. Berlin-Heidelberg: Springer-Verlag.
Fotheringham, A Stewart and Peter A Rogerson. 2008. The SAGE Handbook of Spatial Analysis. United Kingdom: SAGE.
Jiang, Bin and Xiaobai Yao. 2010. Editors. Geospatial Analysis and Modelling of Urban Structure and Dynamics. Dordrecht Heidelberg London New York: Springer.
Lai, Poh Chin, Fun Mun So, Ka Wing Chan. 2009. Spatial Epidemiological Approaches in Disease Mapping and Analysis. Boca Raton, FL.: CRC Press, Taylor & Francis Group.
Lee, Jay and David Wong. 2005. Statistical Analysis of Geographic Information with ArcView GIS And ArcGIS. 2a. Ed. USA: Wiley.
Rogerson, P.A. 2006. Statistical Methods for Geography. 2a. Ed. SAGE Publications: London.
Wang, Fahui. 2006. Quantitative Methods and Applications in GIS. Boca Raton, London, New York: CRC Press, Taylor & Francis Group.
Additional references and other supporting material
Field, A. P. (2005). Discovering statistics using SPSS (Second Edition). London: Sage.
Lloyd, Christopher D. 2007. Local Models for Spatial Analysis. Boca Raton, FL.: CRC Press (Taylor & Francis Group).
O'Sullivan, David y David J. Unwin. 2002. Geographic Information Analysis. USA: Wiley.
Smith, M. J., M. F. Goodchild y P. A. Longley. 2007 (2006) Geospatial Analysis – a comprehensive guide. 2nd edition. Free access at:http://www.spatialanalysisonline.com/output/
Stevens, James 1996. Applied Multivariate Statistics for the Social Sciences. USA: Lawrence Erlbaum Associates.
Waller, Lance A. y Carol A. Gotway (2004) Applied Spatial Statistics for Public Health Data. New York: John Wiley and Sons.
Evaluation. The course evaluation is based on summaries of replicated readings assigned or suggested (45%), computer labs solved (45%), and a final five page paper suggesting a set of articulated techniques to test a research hypothesis in urban planning (10%).
Please do not forget to organize your bibliography in the proper way (APA, MLA, Chicago)
Grading scale
> 93 = A
90 – 92 = A-
87 – 89 = B+
83 – 86 = B
80 – 83 = B-
77 – 79 = C+
73 – 76 = C
70 – 72 = C-
67 – 69 = D+
< 66 = D