Mix of surveys

#1
Hello everyone,

I have a very limited experience in online research and if you have 1 minute to help me, I will be grateful.

Every day I build a probabilistic sample using a list-based sampling frame from a large website accounts list. All these samples have the same volume, 95% confidence level and 3% error margin.
Everyday I send one question to respondents and every of these questions measure one variable. In the same time, every of these questions is considered to be a survey itself (as a survey with one single question). The period of answers gathering is one month for every survey- question.
After the period is closed, I would like to apply correlations tests between any two of these variables. I take into consideration only respondents which answer to both questions.

Do you think it's ok to do that?
I know it might sound like the dumbest thing you ever heard, but please do not kill me :D.Thanks a lot!
 

hlsmith

Less is more. Stay pure. Stay poor.
#2
Do you want to better describe the "probabilistic sample". And are these the people receiving the question?