Help with partial choice set designs

This forum is for posts that specifically focus on Ngene.

Moderators: Andrew Collins, Michiel Bliemer, johnr

Re: Help with partial choice set designs

Postby atan » Mon Oct 02, 2023 3:31 pm

Michiel Bliemer wrote:I have now created a spreadsheet that creates a candidate set with overlapping attribute levels, which is what is needed for a partial profile design.

In the spreadsheet you put in the levels for each attribute and the number of attributes you want to overlap. Note that this number is treated as a minimum, as other attributes may also have overlap. If you prefer a candidate set where an exact number of attributes have overlap, then you can consider removing the undesirable rows from the candidate set.

https://www.dropbox.com/scl/fi/ly03e0kzvwg2i2flcl867/Partial-profile-candidate-set-generator.xlsx?rlkey=1mrp3q1yjgi4tewwh8rp4qwyn&dl=0

If you spot any mistakes in the spreadsheet, please let me know.

Michiel


Hi Michiel,

Thank you for creating this partial profile design candidate set generator. It looks like there is a step 4. missing from the instruction box.

Also, I'd like to confirm the meaning of the "Mininum no. of attributes to overlap in each choice task", does this mean if I input minimum = 1, there is at least one overlap in attributes. Or does it mean, it could be up to as many attributes that we have in our choice task? If I'd like to fix the number of overlapping attributes using this partial profile generator is this possible. e.g. if I wanted to overlap three attributes for all choice tasks?

Thank you in advance,

Annie
atan
 
Posts: 13
Joined: Mon Sep 25, 2023 9:49 pm

Re: Help with partial choice set designs

Postby Michiel Bliemer » Tue Oct 03, 2023 9:34 am

Thank you for the feedback. I have updated the description and renumbered the steps.

If you put overlap to 1, then the spreadsheet guarantees that at least 1 attribute has overlapping levels, but there many be more attributes with overlap because the levels of the other attributes are randomly chosen.

It is not possible to state "exactly 3", the way this spreadsheet works is that it can only do "minimum 3". But of course it is very easy to simply compute the attribute overlap of each row in the candidate set and simply remove the rows that you do not like. This allows you to create a candidate set where "exactly 3" attributes are overlapping.

Michiel
Michiel Bliemer
 
Posts: 1885
Joined: Tue Mar 31, 2009 4:13 pm

Previous

Return to Choice experiments - Ngene

Who is online

Users browsing this forum: No registered users and 38 guests

cron