Spatial Data Analysis

Prerequisites

This module is part of the Social Science Research Methods Course programme which is a shared platform for providing research students with a broad range of quantitative and qualitative research methods skills that are relevant across the social sciences.

This module introduces students to the capture, display and statistical analysis of spatial data. The first two sessions deal with the construction of a geo-database (using secondary data) and data mapping in a GIS (Geographical Information System). The associated lectures include: descriptions of different spatial data types and spatial objects and a review of spatial data quality issues.

Session three asks what is special about spatial data when undertaking statistical analysis and the associated practical looks at spatial autocorrelation – one of the fundamental properties of spatial data. Session four introduces the principles and some of the methods of exploratory spatial data analysis (ESDA). Session five looks at the topic of cluster or “hot spot” detection (identifying areas of excess risk in the context of disease and crime rates). Session six then considers the special issues that need to be recognized when fitting a regression model (to estimate the association between a dependent variable and a set of independent variables) using spatial data. The course concludes with two special topics – session seven looks at non-parametric methods of spatial interpolation (methods for constructing a map from sampled data) whilst eight looks at areal interpolation (methods for transferring data from one spatial framework to another sometimes referred to as the “change of support problem”).

Each session comprises a one hour lecture followed by a one hour practical class.

• Mphil and PhD students from participating departments taking the Social Science Research Methods Centre training programme as part of their research degree

• A basic course in statistics up to and including statistical inference (hypothesis testing; confidence intervals) and regression modelling.

Number of sessions: 8

• Session 1: Building a geo-database
• Session 2: Mapping using a GIS
• Session 3: What is special about spatial data?
• Session 4: Exploratory spatial data analysis
• Session 5: Cluster (hot-spot) detection
• Session 6: Regression with spatial data
• Session 7: Special topics I: non-parametric spatial interpolation
• Session 8: Special topics II: areal interpolation (“change of support”)

• To introduce students to the methods of data analysis that are relevant for spatial data.

• Lectures held in the Small Lecture Theatre, Geography Department, Downing Site (Prof Bob Haining)
• Practicals held in the Top Lab, Geography Department, Downing Site (Dr Gabriel Amable)

GIS software

• Writing up two practicals, submitted as a single written exercise.

Haining, R.P. (2003) Spatial Data Analysis: Theory and Practice. CUP.

• To gain maximum benefits from the course it is important that students do not see this course in isolation from the other MPhil courses or research training they are taking.
• Responsibility lies with each student to consider the potential for their own research using methods common in fields of the social sciences that may seem remote. Ideally this task will be facilitated by integration of the SSRMC with discipline-specific courses in their departments and through reading and discussion.

8 weeks, 2 hours per week. N.B. as this course covers eight weeks of teaching, it is the equivalent of two SSRMC modules.

Once a year in Michaelmas term