This course provides a practical, progressive introduction to biomedical statistics in R, beginning with data types, descriptive statistics, measures of central tendency and variability, and exploratory visualization, then advancing to sampling distributions, the central limit theorem, confidence intervals, bootstrap and permutation methods, hypothesis testing, and comparative analyses for independent and paired data. It also covers categorical-data analysis, non-parametric methods, ANOVA, post-hoc comparisons, interaction effects, MANOVA, Pearson and Spearman correlation, and statistical modelling through simple and multiple linear regression, logistic regression, and count models, with emphasis on model assumptions, effect estimation, uncertainty, and diagnostic assessment.
Course materials
Choose a chapter from the sidebar or the list below.
Chapters
- Preface
- 1 Data foundations and R essentials
- 2 Descriptive statistics and exploratory data analysis
- 3 Sampling distributions and confidence intervals
- 4 Bootstrap and probability models
- 5 Continuous two-group comparison
- 6 Independent two-group example: biomarker change
- 7 Paired t-test and Wilcoxon signed-rank test
- 8 Multiple testing
- 9 Categorical Inference
- 10 Independent categorical outcomes
- 11 Fisher’s exact test for sparse contingency tables
- 12 McNemar’s test for paired binary data
- 13 ANOVA and robust multi-group comparisons
- 14 MANOVA for multivariate continuous outcomes
- 15 Correlation analysis
- 16 Linear regression and diagnostics
- 17 ANCOVA and interactions for continuous outcomes
- 18 ANCOVA with baseline-by-treatment interaction
- 19 Log-scale ANCOVA
- 20 Logistic and count regression
- 21 Logistic regression for a binary outcome
- 22 Model comparison using a likelihood-ratio test
- 23 Poisson and negative binomial regression for count outcomes
- 24 Survival analysis and time-to-event models
- 25 The Art of Choosing Statistical Methods
- References