Key points at a glance
- Define the construct and population before writing a single question.
- Use neutral, single-focus items and response scales that match the analysis.
- Pilot the questionnaire and check recruitment, consent and data protection.
- Report missing data, sample limits and measurement decisions transparently.
Translate the research question into measurable constructs
A survey can only answer questions that its items measure. Define each construct, decide what an observation represents and identify the population to which your claims might apply.
Use existing validated scales when they fit and document adaptations. Creating a new scale requires a clear rationale and more careful interpretation than adding a few intuitive questions.
Write clear and neutral questions
Ask one thing at a time, avoid unexplained terms and specify a useful time frame. Leading wording, double-barrelled questions and overlapping response options create data that are difficult to interpret.
Choose response options that cover the plausible range and include “not applicable” or “prefer not to say” only when they make methodological sense.
Plan sample, pilot and data protection
Explain how participants are reached, what inclusion criteria apply and what the recruitment method means for bias. A convenience sample can be usable when the limitations are stated clearly.
Pilot the survey for comprehension, length, mobile display, missing options and technical problems. Explain purpose, voluntary participation, storage, anonymisation and withdrawal before collection.
Analyse and report the answers responsibly
Define how you will handle missing values, scale scores, exclusions and statistical tests before interpreting the results. Choose analyses that fit the measurement level and sample.
Report response rate, sample composition and uncertainty. Do not generalise beyond the design or imply causation from a descriptive cross-sectional survey.
Final submission context
Formal details can feel like a separate writing task, but they matter just as much for a printed submission. Anything missing, misplaced or inconsistently formatted in the document will also appear in the bound copy.
Use this guide together with your cover page, table of contents, page numbers, source notes and appendices. Prepare the final PDF for printing and binding only after the complete file has been checked.
Practical check before PDF export
- Do headings, chapter structure and page numbers match?
- Are sources, figures and tables included completely?
- Are required elements such as declarations, appendices or the cover page included where required?
- Did you open and check the final PDF after exporting it?
Checklist
- Research question, constructs and items are aligned.
- Questions are neutral, single-focus and understandable.
- Response options match the intended analysis.
- Recruitment and sample limitations are documented.
- The survey was piloted on the actual device or platform.
- Consent, privacy and storage requirements are met.
- Missing data and exclusions are reported transparently.
Common mistakes
- Writing a survey before defining the population and construct.
- Combining two questions into one item.
- Using leading wording or incomplete response options.
- Collecting more personal data than the analysis needs.
- Making representative or causal claims from a convenience sample.
Prepare the survey thesis for submission
After the data, analysis and anonymised materials are checked, prepare the final PDF for printing and binding.
View thesis printing optionsRelated content
Explore related guidance on thesis structure, sources, formatting and final submission.
Frequently asked questions
How many responses do I need?
The required sample depends on the design, population, planned analysis and precision. Use a justified method or discuss the limitation with your supervisor rather than relying on one universal number.
Can I create my own questionnaire?
Yes, if the items are theoretically justified and tested. Existing validated instruments are preferable when they fit your question.
Should I include a neutral middle option?
It depends on the construct and scale. Do not force a position when neutrality or lack of knowledge is a meaningful response, but do not add options without a reason.
Can an online survey be used for a thesis?
Yes, if the platform, recruitment, consent, data storage and sample limitations are appropriate and documented.