Missing data can arise in a number of ways, and it is important to distinguish among these different instances.
     There are at least five missing data situations, each of which should have a distinct missing data code.

1. Refusal/no answer : The subject explicitly refused to answer the question or did not answer the question when he or she should have.
2. Don’t know : The subject was unable to answer the question, either because he or she had no opinion or because the required information was not available (e.g., a respondent could not provide family income in dollars for the previous year).
3. Processing error : For some reason, there is no answer to the question, although the subject provided one. This can result from interviewer error, incorrect coding, machine failure, or other problems.
4. Not applicable : The subject was never asked the question for one reason or another. Sometimes this results from “skip patterns” that occur, for example, when subjects who are not working are not asked questions about job characteristics. Other examples are sets of items asked only of random subsamples and items asked of one member of a household but not another.
5. No match : This situation may arise when data are drawn from different sources (for example, a survey questionnaire and an administrative database), and information from one source cannot be located.

Source: Guide to Social Science Data Preparation and Archiving, ICPSR