mathstatKurssit

Matematiikan ja tilastotieteen laitoksen kurssisivualue

Skip to end of metadata
Go to start of metadata

Analysis of infectious disease data, spring 2008

Lecturer

Kari Auranen

Scope

6 cu.

Type

Advanced studies.

Contents

The preliminary contents is as follows:

Lecture 1

(Powerpoint presentation)

Lecture 2

Introduction to chain binomial models

Lecture 3

More on chain binomial models

Lecture 4a

Bayesien data augmentation forchain binomial models

Lecture 4b

Random effect models

Lecture 5

Continuous time models (estimation of infectiousness and latency)

Lecture 6

Exercises

Lecture 7a

Modelling larger outbreaks

Lecture 7b

"Modelling larger outbreaks" continues (in Finnish)

Lecture 7b

"Modelling larger outbreaks" continues (in English)

Lecture 8

Estimation of vaccine efficacy

Course description

This course gives an introduction to statistical analysis of infectious diseasedata. Examples of typical problems for data analysis include estimation of the (mean) duration of infection or the mean number of secondary cases a case produces during his/her period of infection. The course covers some basic approaches, relying on both the frequentist and the Bayesian paradigms. The latter are particularly convenient for the analysis of infectious disease data, because the data are often incomplete (e.g. the times of infection are not directly observed).

Background material

  • N.G. Becker: Analysis of Infectious Disease Data, Chapman and Hall, 1989
  • R. Anderson and R. May, Infectious Diseases of the Humans, Oxford University Press
  • M.E.Halloran: Concepts of Infectious Disease Epidemiology in Modern Epidemiology, eds. Rothman and Greenland, Lippincott and Raven, 1998
  • Course notes (to be published during the course on this web page)

Exercises

There are three Excercises to choose from. The first one concerns the analysis of the Abakaliki data. The two other excercises deal with models for outbreaks of SARS (exercise II) and common flu (exercise III). Instructions can be found below.

  • No labels