QCBS R Workshop Series
Preface
0.1
Code of conduct
0.1.1
Expected behaviour
0.1.2
Unacceptable behaviour
0.2
Contributors
0.3
Contributing
Generalized linear models in
R
1
Learning objectives
2
Preparing for the workshop
3
Reviewing linear models
3.1
General linear models
3.1.1
Definition
3.1.2
Assumptions
3.2
An example with general linear models
4
Example with real data
5
Recalling linear models: assumptions
5.1
Model prediction
5.2
So, what do we do now? Transform our data?
6
The distributions of biological data
7
Generalized linear models
GLM with binary data
8
Binomial GLM
8.1
GLM with binomial data: logit link
8.2
Example
8.3
Challenge 1
8.4
Interpreting the output of a logistic regression
8.4.1
An example using the identity link
8.4.2
Interpreting the coefficients using the logit link
8.5
Predictive power and goodness-of-fit
8.5.1
Challenge 2
8.6
Visual representation of results
GLM with proportion data
9
Binomial GLM and proportions
GLMs with count data
10
What can we do with count data?
10.1
Poisson GLMs
10.1.1
The Poisson distribution
10.1.2
Poisson GLMs in
R
10.2
The problem of overdispersion
10.3
Quasi-Poisson GLMs
10.4
Negative binomial GLMs
10.5
Plotting the final GLM to the data
10.5.1
Challenge 3
10.6
Conclusion on GLMs with count data
Other distributions
11
Other distributions
Additional GLM resources
12
Summary
13
Additional resources
14
References
QCBS R Workshop Series
Workshop 6: Generalized linear models
Chapter 14
References