Mixed models with medical and engineering applications

A useful reference regarding practical aspects of fitting mixed models in R is Faraway, J.J. (2006) Extending the linear model with R, Chapman and Hall/CRC, chapter 2 and 8.

Details on fitting linear mixed models in SPSS are provided in these notes.

Some data sets and R-code used in the course. The orthodontic data set "Orthodont" is a part of the nlme R package.

Participants are evaluated as passed/failed based on attendance and assessment of hand-ins.

DEADLINE for hand-ins is 12:00 Monday November 4.

1 Wednesday October 16 8.15-12.00: Brush up on variance, covariance and correlation. Slides (with exercises). Exercises to be handed in: 1, 2 and 3.1, 3.2 (3.3 and 3.4 are optional for handing in). Also think carefully about the questions in exercise 4. We'll have a plenary discussion of exercise 4 on Friday.

2 Wednesday October 16 12.30-15:00: Slides (with exercises) and spss-screen shots. Hand-in: exercise 2 and 3.

3 Friday October 18 8.30-12.00: Recap slides. Ordinary and weighted least squares. Mixed models with correlated noise.

4 Friday October 18 12.30-15.30: (attendance not mandatory) you work on exercises and possibly mixed model analysis of your own data. I will be around to help.

5 October 23 8.30-12: online repetition of morning teaching session from Friday October 18 (for those who could not make it on October 18).


Last modified