Applications in veterinary epidemiology
Preamble
Epidemiological Skills for Animal Health Professionals
Acknowledgements
Copyright
Cite
1
Introduction
1.1
Skill requirements
1.2
Structure of this book
1.2.1
Dashboards
1.3
About Ausvet
1.4
TO-DO
2
Reproducible research
2.1
What is reproducible research
2.2
Setting up your R environment
2.2.1
Installing R and RStudio
2.2.2
Use of headers to structure code
2.2.3
Structure of a project directory
2.3
Code repository
2.3.1
Git
2.3.2
Git workflow
2.3.3
What to include in a repository: Git pointers
2.3.4
Collaborating
2.4
Document outputs
2.4.1
Writing out Word documents
2.4.2
Writing out Excel documents
2.4.3
R Markdown
2.4.4
Notebooks
2.4.5
Plumber ??
2.4.6
R packages
2.5
An example of a workflow in practice
3
A framework for data munging
3.1
Data validation
4
R and databasing
5
Spatial data
5.1
Vector data
5.2
Raster data
5.3
Map projections - working with EPSG codes
5.4
Linking to GDAL and other geoprocessing software
5.4.1
installing GDAL
5.5
Constructing Atlantis
5.5.1
Atlantis emerges!
5.5.2
Providing Atlantis with a geography
5.5.3
Populating Atlantis
5.6
Displaying map data
5.6.1
ggplot2
5.6.2
leaflet
5.6.3
interactive leaflet inside bookdown? flexdashboards?
5.7
TODO
6
A regression model stack
6.1
Linear models
6.2
Typical Issues for epidemiological data
6.3
Mixed effect models
6.4
Generalised additive models
6.5
Frequentist vs Bayesian approaches to regression modelling
6.6
A frequentist approach
6.6.1
glmmTMB
6.6.2
mgcv
6.6.3
model selection and averaging
6.6.4
inference with marginal predictions
6.6.5
regression diagnostics
6.7
A Bayesian approach
6.7.1
R-INLA
6.8
regression models for observational studies
7
Clinical trial data
7.1
Non-inferiority tests for ordinal data
7.2
some other case study
8
Case Study
9
Analysis of the epicurve
10
Survival analysis
11
Network Analysis
12
Diagnostic test validation
13
Small area estimation for extrapolating a model
14
Dashboards
14.1
Rationale for dashboards and when to apply them
14.2
Frameworks
14.3
Flex dashboard
15
Speeding up code
15.1
common instances when processing slows down
15.2
code structure
15.2.1
loops
15.2.2
dialect
15.3
use of intermediate objects
15.4
use of pointers
15.5
dynamic loading of compiled code
15.6
scaling up
15.6.1
parallelism
15.6.2
AWS
16
References
Published with bookdown
Applications of statistical analysis within veterinary epidemiology
Chapter 15
Speeding up code
15.1
common instances when processing slows down
15.2
code structure
15.2.1
loops
15.2.2
dialect
15.3
use of intermediate objects
15.4
use of pointers
15.5
dynamic loading of compiled code
15.6
scaling up
15.6.1
parallelism
15.6.2
AWS