Spatial Data Analytics

• Credit value: 30 credits at Level 7
• Convenor and tutor: Dr Shino Shiode
• Assessment: practical coursework of up to 4000 words (100%)

In this module, you will enhance your knowledge and analytical skills for investigating and explaining how various geographical phenomena are distributed and change their patterns across space and time. We begin with core methods and operations for analysing data with spatial or space-time distribution, exploring how to interpret such data and what kind of methods can be used for spatial analytics. We then move on to learning more specialised theoretical knowledge and analytical skills to enable in-depth analysis of spatial phenomena.

The theory and methods covered in this module vary widely across the domain of spatial data analysis, ranging from the conventional spatial and spatial-temporal statistical methods to more recent computational approaches. You will learn these methods by examples to help select and apply suitable techniques for solving spatial problems.

Each lecture will be followed by a practical session which offers hands-on knowledge on how to conduct spatial and space-time analysis using specialist software as well as coding in R language. Each topic will be discussed in the context of a real-world problem, including those in urban, environment, health, transport, business and security.

Indicative syllabus

• Exploring spatial and spatio-temporal data
• Spatial data analysis Using R
• Statistics for spatial data analysts
• Spatial distributions of point events
• Detection of spatial and space-time clusters
• Spatial interpolation and geostatistics
• Association in spatial data
• Spatial autocorrelation
• Spatial regression analysis
• Spatial forecasting

By the end of this module, you will be able to:

• understand the main statistical theory and methods used for describing geographical data
• understand the concept of statistical inference and apply various statistical tests to geographical data
• characterise and analyse the distribution patterns of point data using a series of spatial and space-time analytical approaches
• understand the fundamental characteristics of spatial data and examine the presence of (global and local) spatial autocorrelation in the spatial data
• overview the main geostatistical approaches and carry out spatial interpolation using these methods
• examine the association between variables in spatial data and explain their causal relationship through spatial process modelling
• explain the methodological advantages and disadvantages of the various analytical methods discussed in the module and select a method appropriate for solving a geographical problem in the real-world context
• use the relevant spatial data analytical software and code in R programming language to solve spatial problems
• work successfully with a range of geographical data formats and standards.