Foundations & descriptive analysis
Lessons 01–02L · 01
A Structured Approach to Data AnalysisCausal diagrams, data-collection sheets, coding and entry, file and variable management, and program-mode versus interactive workflows.R walkthrough: Getting Started with R and RStudio.
L · 02
Data Cleaning & Descriptive AnalysesData quality assessment, cleaning strategies, handling missing data, descriptive statistics, and visualization for epidemiologic datasets.R walkthrough: Data Cleaning and Descriptive Statistics in R.
Regression models
Lessons 03–04L · 03
Linear & Logistic RegressionTwo-variable tests and confounding, multivariable linear regression and its checks, logistic regression with odds ratios, calibration and discrimination, and building and comparing models.R walkthroughs: Linear and Logistic Regression in R and Comparing Models and Selecting Variables in R.
L · 04
Generalized Linear ModelsVariable types and the model that suits each outcome, the assumptions of linear regression and how to check them, ordinal and multinomial logistic regression, and Poisson and negative binomial regression for counts.R walkthroughs: Ordinal Logistic Regression in R, Multinomial Logistic Regression in R, Poisson and Negative Binomial Regression in R and Survival Analysis in R.
Dependent data
Lesson 05L · 05
Modelling Dependent DataClustered and repeated-measures data, the ICC and design effect, linear mixed models with random intercepts, GLMMs and GEE for binary outcomes, and repeated measures over time.R walkthrough: Mixed Models and GEE in R.
Exploratory visualization
Lesson 06L · 06
Exploratory Data Analysis and VisualizationThe lesson shows why analysts look at data before modelling, matches displays to questions and variable types, builds quick plots in base R and layered plots in ggplot2, and assembles a captioned multi-panel figure from the Canadian Social Connection Survey.R walkthrough: Data Visualization in Base R and ggplot2.
Measurement & path models
Lessons 07–08L · 07
Measurement and PsychometricsStudents learn how scales and indices turn constructs into scores, estimate reliability with Cronbach's alpha and omega, assemble validity evidence, and fit exploratory and confirmatory factor analyses, with an introduction to item response theory.R walkthroughs: Factor Analysis and Scale Scoring in R and Latent Class Analysis in R.
L · 08
Mediation, Moderation and Path AnalysisThe lesson uses a DAG to separate confounders, mediators and colliders, treats effect modification as a separate question, fits interaction models with simple slopes, estimates indirect effects with bootstrap intervals, and expresses the model as a path analysis in lavaan.R walkthroughs: Mediation and Moderation in R and Path Analysis with SEM in R.