STA530 — Spatial Epidemiology

Interactive study reference and exam-prep tracker

Welcome

This app follows the sessions of STA530 Spatial Epidemiology (University of Gothenburg, autumn 2026): from what makes data spatial, through disease maps and spatial autocorrelation, to spatial regression and Bayesian disease mapping. New sessions are added as the course goes on.

One idea runs through the course: a map is the beginning of the epidemiologic question, not the end. Where is disease high → why is it high there → what can be done?

Foundations and exploratory analysis

Spatial models

How to study with it

  1. Start with The big ideas: the whole course on one page, 18 ideas in one sentence each.
  2. Read a session. Every topic starts with a blue In short box (plain language, often with an everyday comparison) and ends with a yellow On the exam, be able to say box. Formulas have an In words line, and the heaviest derivations are folded away. Every topic has a status control under its heading: Not reviewed / Reviewed / Confident. Click as you go.
  3. Open “Before you start” at the top of each session if a prerequisite feels rusty, and watch for the red Common confusion boxes.
  4. Answer the quizzes in each session and the why-questions at the bottom.
  5. Practise on Exam practice: drills that generate new numbers every time (SMR, indirect standardization, Empirical Bayes weights, box-map fences, counting neighbours, Moran’s I by hand, SAR impacts, exp(β), choosing the likelihood, reading exceedance probabilities) and written exam-style questions with model answers.
  6. Check the dashboard to see what is left, in priority order.
  7. Look up terms in the glossary, or use search (top right).
  8. Go further with Resources: the instructor’s optional videos (Luc Anselin’s spatial regression lectures), books and web pages, each linked to the section it supports.

The exam

STA530 is examined by an individual written exam (2.5 credits, grades U/G/VG) and active participation in a seminar (1 credit, U/G). According to the lecture notes, the exam tests concepts, not programming. So the app focuses on explaining, interpreting and comparing; the R cells are there to build intuition, not as exam material.

What the badges mean

No exam questions have been released yet. The badges show why a topic is likely to matter:

Badge Meaning
🎯 Instructor learning objective Matches a stated learning objective: the course syllabus, the instructor’s Canvas post for the session, or a “Learning goals” slide. Highest priority.
❓ Instructor’s key question Answers a key question the instructor posted, or a question asked on a slide.
✏️ Emphasised in class Written down as important in the lecture notes taken in class.
📌 Likely exam-relevant (AI-inferred) Inferred from definitions, formulas and worked examples on the slides. Not confirmed by the instructor.
📎 Optional depth (beyond course scope) The instructor marked it as optional, or said it is not expected in STA530.
(no badge) Background, examples or summaries. Still course content.

How to read the diagrams

Arrows mean different things in different diagrams, so every flow diagram’s caption starts with its kind:

Caption starts with An arrow means Example
Causal diagram “Directly affects” SAR vs SEM (3.8)
Workflow “Then”: the next step of an analysis. Not causal From OLS to spatial regression (3.9)
Lecture map How the session’s ideas lead into each other. Not causal The disease-mapping logic chain (4.23)

Code blocks marked Run Code are interactive: R runs in your browser, no installation needed. The first run on a page takes a few seconds while R loads.