Module 11 ยท How do you check data quality?
Clean before you compute
By the end of this module you will be able to
- List the data-quality checks to run before any analysis.
- Recognise a logical contradiction in coded data.
- Explain why clean data is part of the analysis, not a chore before it.
CNA is unforgiving of dirty data, because it reads every row as a real case and takes each one seriously. Before you analyse anything, walk this checklist:
- Missing values. CNA needs complete rows, so decide how to handle gaps before you start, not after.
- Duplicates. The same facility entered twice quietly bends the patterns without telling you.
- Coding errors. A stray 2 in a yes-or-no column will be read literally and believed without question.
- Logical contradictions. "Cold chain broken = 1" alongside "Refrigerator functional = Yes" cannot both be true, so go investigate.
Garbage in, confident garbage out
CNA will cheerfully find a crisp, beautiful pattern in mislabelled data and present it with total confidence, like a witness who is very sure and completely wrong. The method cannot tell a typo from the truth. Cleaning is not optional housekeeping. It is part of the analysis.
Reflect
Think about your last messy dataset.
- Where do errors usually creep in: missing rows, duplicates, miscoding?
- What single check would have caught the most problems?