Survey data cleaning calculator
Enter the total responses and how many you remove for each reason. You get the valid responses left and the removal rate.
- Checked against reference values
- Free, no sign-up
- Nothing leaves your browser
Responses and exclusions
All completed or received surveys
Completed unrealistically fast
Identical answers across matrix rows
Repeat responses from the same person
Other exclusions
Interpretation
Collect real answers in a SurveyNinja survey and see them in charts in the report.
Use this template See the questions firstData is not stored — calculation runs in your browser.
Ready-made template
Do it with your own respondents
The “Market research survey” template already has the questions. Put in your company name, share the link and watch the answers come in.
- Copy the template: the questions are written
- Share it by link, QR code or a widget on your site
- Read the results in the report with charts
New accounts get 14 days of Premium features, no credit card.
What is survey data cleaning?
Survey data cleaning is removing responses that would distort the results: speeders, straight-liners in grids, duplicates and incomplete or nonsense answers. Valid responses = total − removed, and removal rate = removed / total × 100%. From 820 responses, removing 38 speeders, 24 straight-liners, 11 duplicates and 17 incomplete ones leaves 730, an 11% removal rate.
How the clean sample is calculated
-
Formula
Valid responses = total responses − excluded responses. Removal rate = excluded / total × 100%.
-
Speeders
Finishing too fast often means low attention to the questions.
-
Straight-lining
Identical answers in grids can be genuine but need checking in context.
-
Removal rate
A high share of exclusions points to problems with the channel or the questionnaire.
Calculation examples
-
Customer survey
- 820 responses
- 90 exclusions
730 valid responses remain; the removal rate is about 11%.
-
Panel fieldwork
- 500 responses
- 85 exclusions
Leaves 415 valid responses, a 17% removal rate. Top up the sample or plan a bigger buffer for the next wave.
What to avoid
-
Removing without rules
Fix the cleaning criteria in advance, otherwise it is easy to distort the result.
-
Treating every straight-liner as bad
Someone who genuinely rates all items the same is not necessarily a low-quality respondent.
-
Not recording why responses were removed
Keep the exclusion categories and their shares for a transparent report.
Next step
Read the answers in a report, not a spreadsheet
Charts are built for you from every answer. Share the report by link or export the answers to Excel, CSV or SPSS.
- Ready questions or AI from a description
- A link for your email or chat, a QR code or a widget on your site
- Charts in the report, export to Excel, CSV and SPSS
Frequently asked questions
What removal rate is normal?
There is no universal norm: it depends on the channel, the audience and your rules. Compare with earlier waves from the same source, and check the questionnaire or the channel when the rate jumps.
What counts as speeding?
Completing the survey faster than a reasonable minimum time. Such a response may mean the person did not read the questions.
How do I set the minimum time?
Run test completions, look at the median time and set a threshold that accounts for the survey length.
Should I remove incomplete responses?
Usually yes for the full analysis. Partial responses can be used for individual questions if the method says so.
How can I reduce bad data?
Shorten the survey, check the mobile interface, add attention checks and use quality respondent sources.
Learn the method
Read how the method works and where its numbers come from.
Turn the numbers into a survey
Start from the “Market research survey” template: the questions are ready.
WooCommerce Post-Purchase Survey: 7 Questions, When to Ask and What to Do Next