Statistical Assistant how-to

How to Clean a Messy Dataset

Clean data makes good results.

Updated By the Career Education Institute Curriculum Team
Quick answer

Clean data makes good results. In short: check; find; fix, then complete the remaining steps below.

Step by step

  1. Check for duplicates.

  2. Find missing values.

  3. Fix formats.

  4. Check ranges.

  5. Flag outliers.

  6. Document changes.

Safety reminders for statistical assistants

  • Protect confidential data
  • Follow data security rules
  • Document changes
  • Report errors

Mean · Median · Mode · Standard deviation · Outlier · Missing data: see the full statistical assistant glossary.

More statistical assistant how-to guides

Learn this in Statistical Assistant trainingTake the practice test
Enroll in trainingTake fit quiz