GRMs
1
About this book
1.1
About the Authors
1.2
Find a problem? Have a question?
2
Introduction
2.1
Linear models - a kind of Generalized Linear Model
2.2
Assumptions of Linear Models
2.3
Reframing Linear Models as Generalized Linear Models
2.4
What happens when we break the assumptions of linear models
2.5
Parameter estimation
2.6
LMs and GLMs in R
2.7
Some definitions
2.8
Conclusion
2.9
Examples
3
How are GLMs “different”?
3.1
Introdution
3.2
Assumptions of a GLM
3.3
Framework
3.3.1
Exponential Dispersion models
3.3.2
Properties of EDMs
3.3.3
Linking the EDM to the explanatory data
3.3.4
Formal definition of a GLM
4
Linear Models
4.1
Introduction
4.2
A “Good” Example of Simple Linear Regression
4.3
A “Bad” Example of Simple Linear Regression
4.4
Summary
5
Logistic Regression
5.1
What is Binomial Data?
5.1.1
Refresher: Bernoulli and Binomial
5.1.2
Representing the Bernoulli distribution
5.1.3
Representing the binomial distribution
5.1.4
What does a bunch of binomial data look like then?
5.2
Why doesn’t OLS work for Binomial Data?
5.3
Link functions we can use
5.4
ED50
6
Poisson Regression
6.1
What is Poisson data?
6.2
Why ordinary least squares does not work for Poisson data
6.3
Link functions for Poisson GLM’s
6.4
Poisson Example
6.5
Problems of overdispersion and solutions
References
Published with bookdown
An Introduction to Generalized Linear Models
References
Dunn, Peter K, and Gordon K Smyth. 2018.
Generalized Linear Models with Examples in R
. Springer.