When you want to use a question for your statistical survey, you have to design also what kind of answer you will collect.
Among the choices you have are:
- binary answers: yes/no , agree/disagree ...
- a scale: "on a scale from 1 to 5, where 1 is "I strongly agree" and 5 is "I strongly disagree" ...
- a list of classes: interval of values (useful when you're askong about a time)
- a list of options, among which only one is to be chosen
- a list of options, among which more than one can be chosen
- a completely free answer
Completely free answers may take some time to write down, and some time to analyse afterwards: you may have to decide to create categories to analyse everything you got.
Nevertheless they can be very interesting as they may introduce new ideas you did not have beforehand.