0 votes
in SoSci Survey (English) by s114201 (150 points)

Hello, I have a survey, which is launched for a few days already. The experiment and control group were split to 60:40 using a random generator with the group assigned as follows:

1 = Experiment group1
2 = Experiment group2
3 = Experiment group3
4 = Control group1
5 = Control group2

and by using the following code in the composition:

$numberrnd = value('ME16'); // Retrieve the random number drawn by ME16

if ($numberrnd > 3) {
setNextPage('FB1');
}

I see the warning in the random generator not to change the codes after data collection has started. However, after further consideration I see the need to change to 70:30 split. Can I still make an adjustment without hurting the data? Maybe by adding to the same random generator another groups and changing the code?

6 = Control group3
7 = Experiment group4
8 = Experiment group5
9 = Experiment group6
10 = Experiment group7

$numberrnd = value('ME16'); // Retrieve the random number drawn by ME16

if ($numberrnd > 3 && $numberrnd <= 6) {
setNextPage('FB1');
}

Please let me know if any changes are possible at this point. Thank you and wish you a nice day :)

1 Answer

0 votes
by SoSci Survey (328k points)

Please let me know if any changes are possible at this point.

Yes, this will work. But please keep in mind that the respondents starting after you did the change, will have a (much) larger probability to be assigned to the experimental group. This could be a methodological issue, because you usually get different people over time. Maybe, it's the better (and cleaner) choice to stay with the 60:40 implementation.

Willkommen im Online-Support von SoSci Survey.

Hier bekommen Sie schnelle und fundierte Antworten von anderen Projektleitern und direkt von SoSci Survey.

→ Eine Frage stellen


Welcome to the SoSci Survey online support.

Simply ask a question to quickly get answers from other professionals, and directly from SoSci Survey.

→ Ask a Question

...