Assign participants to 2 different question groups (treated and controls)

More
2 years 10 months ago #137326 by holch

dgiacometti wrote: First of all I would like to thank you very much for your help. This project is particularly important for me.
1. In the welcoming page in the title, before the usual title there is this word "[external]" just before it. Why is that? Can I just take it out?

I renamed your survey when I imported it and added [external] at the beginning. If you have a lot of surveys and import some surveys from the forum, it is good to be organized. Later, once the problem is solved, I will delete those surveys that I just imported to help in the forum. You could just delete it. However, I highly recommend not just to use this copy of your survey and continue, but rather check what I have done and implement it in your own survey. If you just copy it, you won't learn anything and you will have the same questions next time.

dgiacometti wrote: 2. I tried to run the survey and it seems the program does not randomize between the treated group and the control. Indeed, it looks like the program only show me the TREATED GROUP questions. Possibly there is something still missing?

I think when I tested it worked, for me. I will check again.

dgiacometti wrote: 3. You suggested to activate the survey to run some tests. Isn't it a problem? It says that if I do that I will not be able to add or delete any questions afterwards.... . Maybe I can easily solve this problem re-charging another survey?

You can activate the survey, run some test surveys, check in the results if everything is alright. Once the tests have been run and you need to make changes, you just deactivate the survey. The results in the database will be archived and you can make your chances. When you re-active the survey, you can start with a clean database.[/quote]

dgiacometti wrote: 4. If my understanding is correct you suggest to keep the initial question (after the welcoming page) not hidden and run some tests. I am right? To do that I just have to unflag the hidden question button, right?

Yes, the last thing for me is hiding the questions. Because first I want to see if the code is working. When the question is hidden, I don't see that. So those "helper questions" stay visible during most of my tests. Once I am sure the codes work I hide the question and check if it still works.

I'm not a LimeSurvey GmbH member. I answer at the LimeSurvey forum in my spare time. No support via private message.
Some helpful links: Manual (EN) | Question Types | Workarounds

Please Log in or Create an account to join the conversation.

More
2 years 10 months ago #137328 by holch
Did a test:
- Got rid of captcha which can be extremely annoying when having to test the questionnaire various times. Captchas would the very last thing I would activate when creating a survey. Only once all the rest is working.
- Made question Q1 visible again to check if the generated number is fitting with the group that is shown.
- Marked the option to show the question code (so that I can easily see what group is showing - especially as it is all in Italian)
So I made 5 tests, 3x "2" appeared, 2x "1" appeared. Whenever 2 came up, the questions with a code starting with "CG" showed up, whenever 1 was drawn, the TG questions show up. So this is the desired behaviour.

Please keep in mind that it is not completely unprobable that the first few tests all show the same random number. At the end of the day for each draw the chance is 50% to draw this number. Only with a large number of tests the more or less equal distribution will kick in.

I'm not a LimeSurvey GmbH member. I answer at the LimeSurvey forum in my spare time. No support via private message.
Some helpful links: Manual (EN) | Question Types | Workarounds
The following user(s) said Thank You: dgiacometti

Please Log in or Create an account to join the conversation.

More
2 years 10 months ago #137331 by dgiacometti
I took out the captcha and unflagged the "always hide this question" button. Now I got alternatives and seems to be randomizing properly.

:woohoo:

I will do some more testing in the next hours.

Is that a way to take out the "exit and clear survey" button? Participants must not have this possibility.

Please Log in or Create an account to join the conversation.

More
2 years 10 months ago #137332 by dgiacometti
I have one last issue to solve.

This survey is incetivized.

I will pay one every 5 participants. So 1/5 of the participants will always win but their prize is based on the result of their responses.

Is it possible to create a random draw that determines the winners? Maybe creating a (bar?)code associated with the ip address that just did the survey?

Then I could provide a link to another website and they could insert the code to check if they won or not. And then I could ask for their email to deliver the prize.

If you have any ideas to suggest that provide the same solution they are welcome.

Please Log in or Create an account to join the conversation.

More
2 years 10 months ago #137371 by dgiacometti

Please Log in or Create an account to join the conversation.

Start now!

Just create your account and start using Limesurvey today.

Register now
Join our Newsletter!