Randomization

Hi everyone,

I am trying to figure out how to randomize participants in a 2:1 ratio to
treatment and control. I would also like there to be equal numbers of men
and women in the treatment and control groups. Any ideas on how to go about
doing this?

Thank you!
Emily

Hi Emily,

This is pretty tough to do in real-time (i.e. when a participant is being
registered) and make sure that there is an exact number of participants in
each group. Some options:

  • Use a random number in a hidden value when a participant is being
    registered to group them into treatment and control (i.e. if the random
    number is less than 0.333, they are control otherwise they are in
    treatment). This method assumes there is an equal number of women and men
    being registered and it doesn’t guarantee the exact breakdowwn you want (it
    will be approximately correct, but it will be random).
  • Once all your participants are registered, download the data into
    Excel and then manually randomize them and then use the Case Importer to
    update the cases back on CommCareHQ.

Sheel

··· On Wed, Oct 19, 2016 at 8:48 AM, Emily Haroz wrote:

Hi everyone,

I am trying to figure out how to randomize participants in a 2:1 ratio to
treatment and control. I would also like there to be equal numbers of men
and women in the treatment and control groups. Any ideas on how to go about
doing this?

Thank you!
Emily


You received this message because you are subscribed to the Google Groups
"commcare-users" group.
To unsubscribe from this group and stop receiving emails from it, send an
email to commcare-users+unsubscribe@googlegroups.com.
For more options, visit https://groups.google.com/d/optout.


Sheel Shah
Project Manager | Dimagi
m: +1.781.428.5419 | skype: sheel_shah