How To Design A Questionnaire For A Final Year Research Project
Experiences and motivation: You may be given a title for a project or you may choose your own. Your own background and interests will help you determine the research question.
Literature review: It is very important to know what research has been done in your field so that you can ascertain the value of your contribution (your position in a conceptual framework). Knowledge of any gaps in the literature may guide you to the best research question for your study.
Strategies: Choose a strategy or strategies that will suit your research.
Data generation methods: You may be working from secondary data but most likely will need to gather data by one of these methods.
Data analysis: Use qualitative or quantitative methods depending on the type of data collected.
Designing and administering questionnaires
Many students do projects that use a questionnaire survey to collect data. These must be carefully designed so that the data you collect is meaningful and can be analyzed.
This stage has to follow a careful plan of what your research question is and what hypothesis /hypotheses are you testing.
The control group in the research
You may want to include a control group.
E.g. if you wanted to know the extent to which disabled children from a special school use computers you could survey a group of children of the same age from an ordinary school as a control group.
Types of data
- Surveys can collect written data (qualitative) and measurement data or preferences on a sliding scale (e.g.using the Likert scale).
- These latter two categories of data are classed as quantitative data.
- Can be used in conjunction with interviews.
- The interview can produce qualitative data.
- The questionnaire can produce quantitative data.
The nature of qualitative research
- Qualitative research uses non-probability sampling as it does not aim to produce a statistically significant result.
- Qualitative research aims for breadth as well as depth.
Purposive sampling is often used in qualitative research. When using purposive non-random sampling the number interviewed is less important than the criteria used to select them.
Determine what you need to know
- What exactly do you need to find out?
- What type of question do you want to ask?
- The more structured the question the easier it is to analyze.
- Types of questions (from Bell (1993) p 76, after Youngman (1986))
Linking the survey questions to theory
If you decide to collect survey data via a questionnaire for your project then you need to be able to design the questionnaire with sound theoretical underpinning, a description, and justification of your choice of questions, a sampling strategy, and descriptions of your participants and the number surveyed. And additionally, you must also describe the procedure for collecting the data and consent and ethical considerations in dealing with your participants.
Here is a useful YouTube video on questionnaire design especially for attitude scales.
- What exactly do you need to find out?
- What is your research question? This is a high-level question.
- What are the hypotheses arising from the research question? You will collect data to answer these questions.
- What type of question do you want to ask? The more precise and focused the question the easier it is to analyze.
Pros and cons of questionnaires
– Less cost and time
– Low cost to distribute especially online
– People like answering structured questions without much need for writing
– Social desirability in answering
– People may deliberately lie
–Select from a list you give them
–Offer selected categories such as age categories e.g. 16-25, 26-35, etc
–The respondent is asked to put something in rank order
–Scales are devices to elicit strength of feeling or attitude. A straightforward attitude scale is a Likert scale
Ambiguity, imprecision, and assumption
- Words that appear common sense to you may have a totally different meaning to others
- Be precise in your wording
- E.g. You ask “What type of school does your child attend? And the respondent chooses from a list of types of schools.
- You have assumed that the mother has one child-but she may have several and at different levels of schooling (primary and secondary)
Developing a questionnaire
Usually 3 types of questions:
Factual questions, Questions about opinions, beliefs, and judgments, and Questions about behavior (what people do).
- Avoid any ambiguity in meaning
- Be precise when asking questions-think of the range of possible answers and be sure that your question will elicit the full range
- You bring to your questionnaire design your cultural values e.g. you cannot assume that everyone will be free on a Saturday to answer a survey –some religions worship on a Saturday.
- Memory can play tricks.
- If you ask about something that happened a long time ago like games played at school a younger person would probably remember more than someone older.
- It depends on why you want this question answered-if it is critical that you get as much data from the person as possible then perhaps provide a list of games they can choose from.
- Do not ask leading questions.
- These are usually subjective and often emotive and are guiding the respondent in one direction.
- Double questions should never be asked
- Do you like apples and oranges?
- Yes to one? Or both?
- How do you analyze data from this question?
Appearance, layout, and length
- Questionnaires should be typed or printed.
- Instructions should be clear.
- Spacing between questions helps the reader.
- If you want a limited number of sheets –reduce the copy.
- Keep all response boxes in line towards the right of the sheet.
- Start with straightforward, easy-to-complete questions.
- Be critical with your questionnaire.
Piloting the questionnaire
- Give your questionnaire a practice run.
- Respondents will tell you how long it took.
- You can find out whether the instructions are clear.
- Also whether there are any ambiguous questions.