Survey Data: Design to Analysis
Write better questions, weight responses sensibly and report survey results honestly
A taste of a lesson
Our staff survey asks: 'How satisfied are you with our excellent new benefits and flexible hours?' Is that OK?
It has two problems. 'Excellent' is leading: it tells people what to think before they answer. And it asks about two things at once, benefits and hours, so someone happy with one and unhappy with the other cannot answer honestly. Split it into two neutral questions: 'How satisfied are you with the new benefits?' and 'How satisfied are you with your working hours?', each on the same five point scale. Try rewriting another question from your survey and I will review it.
Written by the teacher as an example. In your lesson the tutor answers your own questions, and like any AI it can be wrong.
What you will be able to do
- Write clear, neutral survey questions and balanced scales
- Estimate a margin of error and plan sample size
- Clean responses and handle missing answers transparently
- Apply and explain weighting to known population totals
- Code open text with AI assistance and human checks
Lesson plan
- 1 Questions that measure what you mean Write and review questions for clarity and neutrality. Start
- 2 Sample, response and margin of error Plan sample size and understand what the margin covers. Start
- 3 Cleaning responses Detect low quality responses and record every cleaning decision. Start
- 4 Weighting Adjust responses to match known population totals. Start
- 5 Analysing scales and open text Summarise rating scales and code free text responses. Start
- 6 An honest survey report Report results with method, uncertainty and limits. Start
Try asking
About this tutor
A tutor for anyone who runs or analyses surveys: customer feedback, staff surveys, research questionnaires or public polls. You will learn to write clear, unbiased questions, choose answer scales, plan a sample and response rate, and calculate a margin of error. Analysis lessons cover cleaning responses, handling missing answers, weighting to known population totals, analysing rating scales appropriately and coding open text, including how AI can help with coding if you check its work. You finish with a short, honest survey report template you can reuse.
Reviews
3.7
3 ratingsSample
- Kwesi B.Sample
The weighting lesson was clear and honest about limits. The AI coding workflow with spot checks is now how we handle comments.
- Imogen R.Sample
Reviewed our staff survey line by line before launch. Found four double barrelled questions I had missed.
- Dmitri V.Sample
Useful material, but I needed advanced help with complex survey designs and it stayed fairly general on that.
About the teacher
Statistics in plain language, from averages to Bayesian reasoning
9 tutors 350 lessons taught Sample
I teach statistics to people who were put off by it the first time. My approach is to start from a question someone actually has, simulate or count our way to an answer, and only then name the formula. I have worked as an analyst on survey and health research projects, so I have a soft spot for messy samples,...
See Lina's profile and tutorsMore like this
Other tutors on the same or nearby topics.