I am having some difficulties in constructing my random factor in lme4. My experiment design is the following: I have 3 groups of several individuals each. In each group, some individuals were selected for receiving a treatment (experiment) and others were not (control). A measure X was collected several times for each individual.

I would like to know if there is a difference between the individuals who received a treatment and those that did not. But beforehand, I need to make sure that I am assessing my model correctly:

  1. The hierarchical model is the following: Treatment/groups/individuals
  2. In lme4 this would be: X~Treatment*times +(1+ Treatment|groups:individuals)

Am I right?

Thank you in advance for your help.

  • $\begingroup$ What is the role of 'times'? To gather more data under the same condition or do you expect a learning/time effect? $\endgroup$ – Michael M Oct 8 '17 at 12:10
  • $\begingroup$ Time correspond to each measurement of X. I expect to see a variation (or a higher variation) in time for individuals with treatment than those without treatment. $\endgroup$ – Bas Oct 9 '17 at 2:59

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.