How to design survey questionnaires in research
1. Determine the purpose of the survey.
What type of information do you want to collect through the survey? What is your primary purpose? Is the survey the best way to collect that information?
Formulate survey questions. You can ask one question or several questions, but they should be focused on the focus of the survey.
Formulate one or more hypotheses that you want to test. The questions in the survey should aim to systematically test the hypotheses.
2. Choose one or more question types.
Depending on the information you want to collect, there are many types of questions that can be included in a survey, each with its own strengths and weaknesses. Here are some common types of questions used in surveys:
Dichotomous questions
Open-ended questions
Rating questions
Rating questions
3. Write your survey questions.
Your survey questions should be clear, concise, and direct.[9] This will ensure you get the best responses from your respondents.
Keep your questions short and simple.
Ask only one question at a time.
4. Limit the length of your survey.
Try to keep your survey short. You have a better chance of getting a response with a short survey, so you want to keep it as short as possible while still capturing the necessary information. If you can keep your survey to just 5 questions
5. Identify your target audience.
Is there a specific group of people you want to target? If so, it is best to identify this before distributing your survey.
Think about whether you want to collect information from both men and women. Some studies only survey men or women.
Decide whether you want to collect information from adults as well as children. Many surveys are targeted to a specific age group.
6. Make sure you have privacy in place.
Plan to protect the privacy of your survey respondents before you start writing your questions. This is a crucial part of many research projects.
Consider making your survey anonymous. You may want to leave out the names of your respondents. This is a step you can take to protect your respondents’ privacy, but you can still make inferences about their characteristics based on other demographic information (such as age, physical characteristics, or ID numbers).
Consider de-identifying your respondents. Give each survey (and thus each respondent) a unique number or letter, and use these letters and numbers as a new identifier. Remove any personal information that could be used to identify someone.
Remember that you don’t need to collect a lot of demographic information to identify someone. People may be reluctant to provide this information, so you’ll have a better chance of finding more respondents by asking fewer demographic questions (if possible).
Be sure to remove any identifying information after the survey is complete.