MULTILEVEL STATISTICAL MODELLING FOR HANDLING RECURRENCE, RANDOMIZED BLOCK DESIGNS AND CLUSTERED DATA IN EPIDEMIOLOGY (2020)

Organizer: Jan Brink Valentin, Senior Statistician, jvalentin@dcm.aau.dk

Lecturers: Jan Brink Valentin

ECTS: 2.5

Time: 9th, 10th and 14th of September 2020 from 08.30 to 16.00

Place: Department of Clinical Medicine, Søndre Skovvej 15, Auditorium B

Zip code: 9000

City: Aalborg

Number of seats: 40

Deadline: 19th august 2020

Description: Randomized block design is a state-of-the-art method for minimizing random error and, thus, sample size in clinical trials. However, to fully benefit from such designs requires multilevel statistical modelling. In addition, multilevel approaches are also valuable tools for relaxing the independence assumption within certain data clusters. Such clusters could be hospitals or simply reoccurring subjects or both. In the course, you will learn different approached for relaxing the independence assumption, how to handle nested and crossed effects, how to interpret the models and how multilevel designs can be applied in prediction studies. The course covers the following topics:

  • What is multilevel regression and when to use it?
  • Multilevel designs incl. nested and crossed designs
  • Cluster-robust variance estimators
  • Random effects
  • Mixed effects and crossed random effects regression
  • Multilevel linear, Poisson, logistic, Cox and quantile regression
  • Prediction with multilevel regression models
  • Randomized block designs; sample size estimation, execution and analysis.

Literature: Course material will be send out during the course

Prerequisites: Basic Statistics and basic programming abilities with Stata or R, all participants must bring a laptop with either Stata or R installed

Evaluation: Assignment with oral presentation in groups of 3-4 participants

Important information concerning PhD courses: We have over some time experienced problems with no-show for both project and general courses. It has now reached a point where we are forced to take action. Therefore, the Doctoral School has decided to introduce a no-show fee of DKK 3,000 for each course where the student does not show up. Cancellations are accepted no later than 2 weeks before start of the course. Registered illness is of course an acceptable reason for not showing up on those days. Furthermore, all courses open for registration approximately four months before start. This can hopefully also provide new students a chance to register for courses during the year. We look forward to your registrations.