Two Rough Approximations in Information Tables Containing Missing Values

Abstract

A method of possible equivalence classes was developed to deal with missing values. To deal with imprecision of rough approximations that comes from missing values, the concepts of certainty and possibility were used. When an information table contains the missing values, two rough approximations, certain and possible ones, are obtained. The actual rough approximation is located between the certain and possible rough approximations. The method gives the same results as a method of possible worlds. This is a justification of the method of possible equivalence classes.