Partitioning an MaxDiff survey to online and paper-and-pencil respondents

Question

Hello all,

A doubt that has crossed my mind and that I couldn't completely solve by reading the documentation is the possibility of, when generating the design file for a MaxDiff survey, choose how many respondents would answer online, and how many would answer via paper-and-pencil questionnaires.

Let's suppose I'll have a total of 300 respondents (200 online and 100 via paper-and-pencil questionnaires). Basically, I don't know if it is possible to set these numbers "a priori" (set 300 on the "Number of Versions" option, in the "Design Settings" box, and choose those 200/100 numbers after, I don't know how) , or the best way to achieve this is to create 2 similar designs, in which the only difference would be the "Number of Versions" (200 for one and 100 for the other).

Anyone has a hint on this? (I'm using SSI Web 7.0.26)
Best regards,
João Fernandes

Answer 1

The short answer to your question is that no, there is no way to separate versions of your design for online versus printing off.

For a longer reply, you could make paper and pencil files with all 300 and then choose to print off the last 100, ignoring the first 200.  You could also make a second study with a small number of versions to manage for paper and pencil fielding, and then merge the two designs together (i.e. 1-200 versions from the web study, and then something like 1-10 versions from the paper and pencil study become versions 201-211.  In my experience it's not terribly important that you get a 1 to 1 match on respondents and versions, and 300 versions is an arbitrary default in the software.

Comments

Thanks for the enlightenment, Brian. My only question is how can I merge two different questionnaires? I found this on the documentation, but I don't know if it is what I'm looking for:

"Respondent Numbering

You can choose from five options for assigning respondent numbering.  This lets you specify how the respondent numbers (case IDs) are to be generated.  User Name is one of the passwords from the passwords module.  You should only choose this if these values were purely numeric (no letters). Password is also one of the passwords from the passwords module.  You should also only use this if the passwords were purely numeric (no letters).  Internal Interview Numbers are those that the system assigns when respondents complete the survey over the Web.  There can be gaps in the sequence if some respondents started a survey but didn't finish.  Sequentially Assigned Numbers (default) are integers 1 through n.  Other lets you choose another numeric variable to use for respondent numbering.  This last option is useful if you are linking surveys from another source and need to merge the data sets by a "passed-in" variable."

---

Conjoint designs can be exported to a CSV file in the conjoint exercise setting.  If you are in version 7, respondent answers are text files you can copy and paste together with something like Notepad.  If you are in version 8, respondent answers are in a CSV file and can be merged together with Excel.