Essential Statistical Skills for Public Health Practice

Quantitative literacy has become an indispensable skill for researchers, clinicians, policy analysts, and students across the health and social sciences. Yet a persistent gap exists between statistical textbooks that assume prior programming expertise and those that sacrifice rigour in the name of accessibility. This book is designed to occupy exactly that middle ground — rigorous enough for postgraduate study and professional research, yet accessible enough for anyone encountering R for the first time.

Using R, the world's leading open-source environment for statistical computing, this book guides readers through a coherent analytical workflow from raw data to publication-ready results. Grounded in real and realistic public health datasets, every concept is illustrated with executable R code that readers can replicate, adapt, and build upon. The emphasis throughout is on practical application, reproducible analysis, and clear interpretation of results — not just on running procedures.

Key features:

• Comprehensive coverage of data management using the tidyverse suite, including importing, cleaning, reshaping, and handling missing data
• Step-by-step data visualisation using ggplot2, covering bar charts, violin plots, histograms, and combination plots for categorical and numerical variables
• Descriptive statistics including measures of central tendency and dispersion, with visual interpretation
• Hypothesis testing frameworks with decision flowcharts, covering matched and unmatched two-group and multi-group tests, including ANOVA and non-parametric alternatives
• Survival analysis using Kaplan-Meier curves and Cox proportional hazards models
• Regression modelling including OLS linear regression, logistic regression, and probit regression with model evaluation techniques
• Complete meta-analysis workflow across two dedicated chapters, including forest plots, subgroup analyses, meta-regiression, publication bias assessment, and Bayesian meta-analysis
• Dimension reduction and unsupervised learning through Principal Component Analysis, k-means clustering, hierarchical clustering, and DBSCAN

Written by an international team of public health researchers, biostatisticians, and data scientists, this book is an essential companion for MSc and PhD students, academic researchers, and public health practitioners who wish to develop confident, reproducible analytical skills in R.