The main goals of this book are to explain, discuss, and apply both the Classical/Frequentist and Bayesian statistical frameworks to fit the different types of Generalized Linear Mixed Models that allow an analysis of the types of data commonly gathered by researchers in the Life Sciences scientists.
The Generalized Linear Model (GLM) has become the essential tool for the analysis of experimental and observational data gathered by advanced students and researchers in the life sciences. The Generalized Linear Model has been extended to incorporate random or population-level effects to take into account a diverse array of data structures that allow the incorporation of experimental or survey design in data analyses; these are the Generalized Linear Mixed Models (GLMM).
The book aims to present the material in an intuitive, approachable, and progressive manner suitable for research scientists and graduate students with only a very basic knowledge of calculus and statistics. The book covers the material in a theoretically rigorous manner, focusing on the practical applications of all the methods to actual research data.
Part I: The conceptual basis to fit statistical models.
1. The purpose of statistics.
2 Statistical modeling and a short historical background.
3. Estimating parameters: the main purpose of statistical inference and how it is done.
Part II: Using the Generalized Linear Model for many data types.
4. The General Linear Model I: continuous explanatory variables.
5. The General Linear Model II: discrete explanatory variables.
6. The General Linear Model III: interactions between explanatory variables.
7. One, two and more models fitted to the data: model selection.
8. The Generalized Linear Model.
9. When the response variable is binary.
10. When the response variable are counts, often with many zeros.
11. Further issues involved in the modeling of counts.
12. Models for positive, real-valued response variables: proportions and others.
Part III: Incorporating experimental and survey design using mixed models.
13. Accounting for structure in mixed/hierarchical models.
14. Experimental design in the Life Sciences - just the basics.
15. Mixed/hierarchical models and experimental design data.