Consolidated index of video content
April 2, 2024 ยท View on GitHub
Week 1 Introducing R and friends
These were made for the class Geog 315, but are equally applicable to this course
Introducing R and RStudio
- Overview of lecture 1m21s
- What R and RStudio are 3m27s
- Origins of R 2m15s
- Overview of RStudio interface 3m34s
- Some basic concepts in R 5m38s
Handling basic data in R
- Values, vectors and dataframes 4m37s
- More about dataframes 2m22s
- Manipulating values as single objects 3m18s
- Plotting data 4m56s
Packages including sf and tmap
- Installing and loading packages 6m27s
- Reading and plotting spatial data with
sf2m54s - Making maps with
tmapand wrap up 2m41s
Week 2 Making maps in R
Lecture on 'spatial is special'
- Introduction
- Spatial heterogeneity
- Spatial dependence (the first law...)
- Scale
- Modifiable areal unit problem (MAUP)
- Course topic overview
Practical materials on making maps in R
These were also made for Geog 315, but again are equally applicable to this class
How to use the tmap functions
- Introduction to tmap (2:58 min)
- Colour palettes 1 (3:15 min)
- Colour palettes 2 (6:36 min)
- The number of classes (3:27 min)
- The classification style (7:24 min)
- Other map frills (2:50 min)
Selecting and tidying data
- Filtering and selecting data (6:07 min)
- Mutating data (3:09 min)
- Pipelines (10:17 min)
Week 3 Spatial processes
Lecture on 'the idea of a spatial process'
- Introduction
- Spatial dependence
- Starbucks...
- First order trends
- Second order effects
- But in the real world they are jumbled up
- Pattern as sample from a population
- The phonebook process
- A null process: the Poisson point process
- A bunch of other processes
Practical materials on spatial processes
Week 4 Point pattern analysis
Lecture on point pattern analysis
Density methods
- Quadrats overview
- Quadrats gadget demo
- Pros and cons of quadrats and challenges of density
- Kernel density estimation
Distance methods
Statistical evaluation
- Simple methods - quadrats and mean nearest neighbour
- Simulation envelopes for distance functions
- Taking potshots at statistics
- Arm waving about likelihood
Overview of lab on point pattern analysis
- Introduction
- See also these short video clips on the practical material from last year (2020)
Crazy hands on quadrats exercise
Week 5 Spatial autocorrelation
Lecture on spatial autocorrelation
Lecture
- Overview
- Nearness and relatedness
- The scatterplot
- Moran's index and statistical evaluation
- Local indicators (LISA)
- Other odds and ends (scale and neighbourhood)
Show and tell
Overview of lab on spatial autocorrelation
This is from 2020 but covers things pretty well.
Week 6 Simple interpolation methods
Lecture on simple interpolation methods
These are from 2020, but are much better than the confusion caused this year by trying to zoom from two computers at once!
Week 7 Geostatistics
Lecture on geostatistical methods
Once again these are from 2020, but are better quality than we get from zoom recording the face to face lecture.
- Introduction
- Trend surface analysis
- Variography
- The maths of kriging
- Outcomes from kriging
- Interpolation evaluation
- TINs and KDE
Week 8 Multivariate analysis
New for 2021 - some wild digressions mean these are a bit choppy, but all the core material is there.
Context
- Introduction (4:43)
- The challenge of the San Francisco dataset and looking ahead to clustering (3:37)
- Some basic plots (2:26)
- Maps and multivariate data (3:51)
Visualization and high dimensional data
- Some scientific viusalisation approaches (10:07)
- Data complexity and graphical dimensions (2:31)
- High dimensional data (3:43)
- The
tidyverserevisited (9:55)
Principle components analysis (PCA)
- PCA in theory (4:02)
- PCA in practice (9:47)
Clustering analysis
- Clustering in theory (7:06)
- K-means (7:11)
- This one is from the 2020 vault, as I somehow lost 2021's video Hierarchical clustering (6:16)
- Geodemographics (6:05)