Abstract
Rough approximations, which consist of lower and upper approximations, are described under objects characterized by possibilistic information that is expressed by a normal possibility distribution. Concepts of not only possibility but also certainty are used to construct an indiscernibility relation. First, rough approximations are shown for a set of discernible objects are shown by using the indiscernibility relation. Next, a set of objects characterized by possibilistic information is approximated. Consequently, rough approximations consist of objects with a degree expressed by an interval value where lower and upper degrees mean the lower and the upper bounds of the actual degree. This leads to that the complementary property linked with lower and upper approximations holds, as is valid under complete information.
