Hi Thais,

Please, see below:



On 14 April 2016 at 23:13, Thais Minett <[log in to unmask]> wrote:
Dear Anderson,

Thank you for your information. I do have some covariables that I want to include in the model such as age, sex and education. So, could you please then confirm which of the two designs below I need for my EVs?:

A)
Group           EV1                   EV2                 EV3     EV4            EV5
(all one)               no dementia    dementia           age             sex            education
1                       0/1                   0/1                 demined         demined        demined

And I then use -D in randomise.

This design is fine, but here you don't use -D. To test the effect of dementia, the contrasts are:

C1: 1 -1 0 0 0
C2: -1 1 0 0 0
 

or

B)
Group           EV1                 EV3      EV4             EV5
(all one)               dementia      age            sex             education
1                       0/1                 demined    demined    demined

And I then use -D in randomise.

This design is also fine, but here you must use -D. To test the effect of dementia, the contrasts are:

C1: 1 0 0 0
C2: -1 0 0 0

All the best,

Anderson

 

Regards,

Thais Minett