01 / Reading Guide
Reading Guide
Who this book is for
For graduate students and prepared advanced undergraduates analyzing modern biological data. It connects statistical reasoning with exploratory graphics and executable analysis. It suits readers who already know elementary tests and want to understand why a model fits a biological question, how its assumptions can fail and how to communicate the resulting uncertainty.
Prerequisites
Undergraduate probability and statistics, linear algebra and working familiarity with R. Review distributions, hypothesis tests and matrix notation before attempting the multivariate and generalized linear model chapters.
What it covers
Generative models, visualization, mixtures, clustering, hypothesis testing and multivariate methods lead into count data, generalized linear models, networks, trees, images, supervised learning and experimental design. Biological datasets make the relationship between measurement technology, data structure and inferential choices explicit throughout the progression.
How to use it
Reproduce one analysis with the supplied data before changing its parameters. Write down the observational unit, sampling mechanism and target quantity, then simulate a small dataset under the proposed model. Inspect residuals and compare an alternative analysis. Keep preprocessing decisions in the script, use independent validation where appropriate and explain what each plot contributes to the biological argument.
Edition and sources
The authors provide the complete online book, citing the 2019 Cambridge University Press publication and ISBN 9781108705295. The online version updates software and examples independently of the printed book. It is available under CC BY-NC-SA; record package versions when reproducing an analysis.
