Conjoint Analysis with ODK

Hello,

I am new to ODK and trying to figure out if I could program a conjoint analysis design using the ODK software. The basic idea is to have two tables side-by-side, where each row in a table is a different attribute and each cell in the table is a level of that attribute.

Anyone have experience doing something like this? The key is that the levels that are displayed to the participant are randomly selected in each survey, and the order in which the attributes appear in the table is also randomly determined (this second point is less important).

-- JT

Juan,

You can't really do tables in ODK Collect, but you can probably do
conjoint analysis with some combination of randomization
(https://groups.google.com/d/msg/opendatakit/0GLJXZtXdVU/MpBruYtu0HUJ)
of questions or pre-loading
(http://xlsform.org/#how-to-pull-data-from-csv) pre-randomized data.

Yaw

··· On Tue, Oct 11, 2016 at 5:50 PM, wrote: > Hello, > > > I am new to ODK and trying to figure out if I could program a conjoint analysis design using the ODK software. The basic idea is to have two tables side-by-side, where each row in a table is a different attribute and each cell in the table is a level of that attribute. > > Anyone have experience doing something like this? The key is that the levels that are displayed to the participant are randomly selected in each survey, and the order in which the attributes appear in the table is also randomly determined (this second point is less important). > > > > -- JT > > -- > -- > Post: opendatakit@googlegroups.com > Unsubscribe: opendatakit+unsubscribe@googlegroups.com > Options: http://groups.google.com/group/opendatakit?hl=en > > --- > You received this message because you are subscribed to the Google Groups "ODK Community" group. > To unsubscribe from this group and stop receiving emails from it, send an email to opendatakit+unsubscribe@googlegroups.com. > For more options, visit https://groups.google.com/d/optout.

Hi all! I'm working on a conjoint analysis for a project in Kenya and thought I'd share an example which could be helpful to others. This randomly selects different attributes to display. As @yanokwa mentioned, it takes advantage of randomization and pulling data from a csv. I used 2 attributes but one could easily use many more with the addition of more random numbers and more columns of the attributes csv!

conjoint_example.xlsx (11.7 KB)
attributes.csv (77 Bytes)

2 Likes