Missing values can compromise your data’s integrity. Empty spaces introduce uncertainty – is there supposed to be data here or not? Missing values can also bias your results. Consistently recording known absences can help.
Common Ways to Record Absent Values
Before using any of these common labels for missing data, check to see if your data collection or analysis tool has a standard way to record missing or null values. Many do and they vary.
- NA – not applicable or not available in this case
- 0 – we took a measurement and it was zero
- NULL – there should be a value here but there isn’t
Tips for Avoiding Mysterious Blanks
As with all data management, consistency and documentation are your friends.
- Note missing values as you go so you have a chance to collect that data before it’s too late.
- Record absent values consistently and define any markers or codes in your data documentation.
- If you have different kinds of absent values, you may need to use more than one code. That’s ok, but again, be consistent.
All Data Nudges are licensed under CC BY 4.0. You are free to share, adopt, or adapt them and cite the Illinois Research Data Service.