This CPD-certified workshop was for early career mental health researchers and data scientists to learn epidemiological methods using R programming. It was part of a series focusing on innovative data science approaches in mental health research, hosted by DATAMIND and MQ, in collaboration with HDR. Led by experienced mental health epidemiologists and R data specialists, the workshop covered study design, causal inference, and basic to intermediate analysis methods in a mental health research context.
Introduction by Naomi Launders
Introduction to the day, aims, and objectives, outlining the structure of the workshop
Understanding observational epidemiology and its implications
Overview of the main steps in a study: design, conduct, analysis, and interpretation
Study Design Part 1 by Ellen Thompson
Exploring different types of studies and data, defining the research question, and cohort definition
Study Design Part 2 by Ellen Thompson
Understanding sample size, power considerations, and addressing missing data in study design
Analysis Part 1 by Naomi Launders
Exploring prevalence, incidence, ratios, and proportions
Introduction to hypothesis testing, confidence intervals, and p-values
Overview of univariable regression techniques: linear, logistic, Poisson
Introduction to univariable survival analyses including Cox and other models
Causal Inference by Annie Jeffery
Understanding the association and causation in epidemiological research
Addressing sources of bias/error, confounding, and Directed Acyclic Graphs (DAGs)
Analysis Part 2 by Annie Jeffery
Techniques for adjusting for confounders through multivariable analysis
Exploring effect modification and mediation analysis techniques
Ready to explore and expand your understanding further? Head back to our learning hub to discover more videos and broaden your knowledge!
