- Created by: Avneet Aulakh
- Created on: 21-02-19 14:17
Types of questions
Avoid open questions which allow a wide variety of responses
E.g. 'What do you think about programmes on TV'
Use closed questions to restrict the replies given
E.g. 'Are you over 18 years old?'
Avoid leading or biased questions which might lead the respondent towards the answer that you want or expect
Rules for designing questionnaires
Make questions clear and closed
Avoid open questions
Don't ask leading questions
Have response boxes which are unambiguous
Have response boxes which cover all possible replies and don't overlap
Pilot surveys are used to test questions in questionnaires, to make sure that respondents understand the questions and can answer in ways that will collect all the data needed and give valid results.
Pilot surveys are usually carried out on a proportion of the total sample population
Random response method
People do not always answer questions truthfully, especially if a questionnaire asks a sensitive questions. This means results might not be accurate.
The random response methods uses a random event, such as tossing a coin, to obtain truthful answers.
For example, if you asked 50 students:
" Toos a coin, if it lands on heads, tick 'yes' below. If tails, answer the question truthfully: Have you ever been bullied? Yes or No
You would expect 25 students out of 50 to have tossed heads, so they will tick Yes. If your result shows that 34 have ticked yes, then about 9 of the students who ticked yes have been bullied. So you can estimate that 18 of the 50 have been bullied.