Respondents may feel comfortable to reveal personal/confidential information because researcher is not present.
Open questions can provide unexpected, more detailed answers which can lead to further research.
No special training needed.
High reliability for closed questions.
Reduces experimenter bias found in interviews.
Weaknesses:
Participants may lie on a questionnaire to present themselves positively ( demand characteristics - social desirability).
Sample can be biased due to who is willing to fill it out.
Questionnaires using closed questions limit the responses -> easier to analyse.
Can take a lot of time to design.
Can only be filled out by those who can read and write.
Response bias.
Types of Closed Questions:
Likert scales
Rating scales
Likert Scales:
Must be carefully constructed as an odd number of response options may cause the middle value to be selected more regularly - even numbers would force participants to make a choice.
Response bias - if statements are all worded favourably then people may agree or disagree constantly. - You can reverse the statements to overcome this.
Have an equal number of agree and disagree options.
Change the order of agree/disagree responses so participants don't mindlessly choose the same option each time.
Writing good questions:
Don't use double negatives and/or double-barrelled questions.
Don't use leading questions which make one answer more attractive than the other.
Questions need to be written so they are easy to analyse.
Include some irrelevant (filler) questions to distract the respondent from the main purpose of the questionnaire.
Start with easy questions
Carry out a pilot study - Test the questions on a small group of people.
Questionnaires:
Set of written questions designed to collect information.
Always pre-determined (structured).
Can discover what people think or feel (No guessing work like observations).
Can provide either qualitative or quantitative data.
Two types of questions:
Open -> Up to respondent how to answer, usually produces qualitative data.
Closed -> Limited in how to respond, usually produces quantitative data.