← Back to series HSCI 341

Fundamental Epidemiological Concepts and Approaches

Office Hours — the companion podcast for HSCI 341

Each episode is meant for listening after the lesson. Sarah and Kiffer add perspective and critique, work through the questions students tend to find most difficult, and add further worked examples, including some that are harder than those in the lesson. Every page has the audio with a visual companion and captions, a summary, a list of chapters and a downloadable transcript.

Foundations, surveillance & sampling

Lessons 01–02

Introduction & Causal ConceptsSarah and Kiffer revisit John Snow's water company comparison, average treatment effects, collider bias and attributable fractions, and debate the Bradford Hill viewpoints.

Surveillance and SamplingSarah and Kiffer examine testing artefacts in passive surveillance, sensitivity and predictive value in syndromic alerts, survey weights, cluster sample sizes, and non-probability samples.

Measurement

Lesson 03

Questionnaire DesignSarah and Kiffer examine non-response bias, attenuation from random measurement error, the influence of response options on answers, and the debate over averaging Likert responses.

Measures & tests

Lessons 04–06

Measures of Disease FrequencySarah and Kiffer work through rates above one, rising prevalence with falling incidence, outbreak case fatality, and standardized rates and SMRs, then debate disability weights.

Screening & Diagnostic TestsSarah and Kiffer work through predictive values, the spectrum effect, likelihood ratios, series testing with shared errors, screening biases and the debate over routine depression screening.

Measures of AssociationSarah and Kiffer work through odds ratios in case-control studies, relative and absolute effects, attributable fractions for radon and smoking, and the debate over statistical significance.

Designing against bias

Lesson 07

Designing Against Bias: Validity and Confounding in Study ProtocolsSarah and Kiffer work through colliders and mediators, response rates and selection bias, misclassification with several categories, and the debate over E-values for unmeasured confounding.

Time-to-event data

Lesson 08

Time-to-Event DataSarah and Kiffer work through immortal time, Kaplan-Meier bookkeeping, competing events and hazard ratios, then debate whether the hazard ratio belongs in the headline.