Lecture 3 - Mapping and Modelling Geographic Data in R

Mapping and ModellingGeographic Data in R

Lecture 3

Measuring spatial autocorrelation

Part 1, Intro to R Intro to statistics Intro to regression

Part 2, Mapping in R

GeographicalDataScience

Part 3, Spatial analysis in R

A map

Is a tool of visualisation, communication and (analytical) exploration

It can show geographical patterns...(which may suggest a process)

Are there patterns in these maps?

Spatial clustering?

Spatial heterogeneity?

Permutation

Are there patterns in these maps?

Spatial clustering?

Spatial heterogeneity?

Moran's I

The correlation between:a measured attribute of locationsandthe same attribute of those locations average neighbour

Luke 10: 29b

What happens to the Moran value if you change the definition of neighbours (or the weight attached to them?)

A spatial statistic

Note how the spatial weights are a part of the calculation.

Here, the I value is decreasing with 'distance'. Why?

Tobler'sFirst 'law' ofgeography

"Everything is related to everything else, but near things are more relatedthan distant things."

source: https://en.wikipedia.org/wiki/Waldo_R._Tobler

Here, the I value is decreasing with 'distance'. Even if we assume that the nearest neighbours approach is the right one, what cut off of k should be chosen?

Vs

'Local'

'Global'

The line represents the overall (global) trend

Each of the points represents what is happening at a local sub-space of the map

The line represents the overall (global) trend

LOW-HIGH

HIGH-HIGH

LOW-LOW

HIGH-LOW

Each of the points represents what is happening at a local sub-space of the map

We will also look at

Getis and Ord G-Statistic based on the proportion of the total sum of standardised attribute values that are within a threshold distance See https://pro.arcgis.com/en/pro-app/latest/tool-reference/spatial-statistics/h-how-hot-spot-analysis-getis-ord-gi-spatial-stati.htm

Anyquestions?