A study of incomplete data – A review

Abstract

Incomplete data are questions without answers or variables without observations. Even a small percentage of missing data can cause serious problems with the analysis leading to draw wrong conclusions and imperfect knowledge. There are many techniques to overcome the imperfect knowledge and manage data with incomplete items, but no one is absolutely better than the others. To handle such problems, researchers are trying to solve it in different directions and then proposed to handle the information system. The attribute values are important for information processing. In the field of databases, various efforts have been made for the improvement and enhance of database query process to handle the data. The different researchers have tried and are trying to handle the imprecise and/or uncertainty in databases. The methodology followed by different approaches like: Fuzzy sets, Rough sets, Boolean Logic, Possibility Theory, Statistically Similarity etc.