Missing data are a pervasive problem in statistics. There are many methods for handling the problem, most of which require laborious numerical calculations. The most common approach to statistical analysis with missing data is complete-case analysis. Complete-case analysis uses cases for which all variables are present. The advantage of this approach is simplicity, because standard statistical analysis can be applied without modification for incomplete data. The disadvantage is the loss of information in discarding incomplete cases. The purpose of this article is to present a new method for deliverance of discarded, incomplete cases. The new method shows an achievement not possible to date  - extracting predictiveness in the entirety of  the discarded incomplete cases. Case studies are discussed.