This lecture-style workshop will introduce relevant concepts and techniques for modelling cross-sectional data observed on regular (such as remote sensing pixels) or irregular (such as Census polygons) lattice. Such data often exhibits spatial dependence and is common across several fields.

We will cover the following topics: motivating examples from time series; spatial random fields and stationarity; spatial autocorrelation measures including Moran’s I; neighborhood or adjacency matrices that capture spatial dependence; and spatial autoregressive models including their estimation and interpretation.

Please note that the material will be discussed in a lecture style presentation with little or no hands-on components.  You should know linear regression well.