Quality of histograms as indicator of approximate query quality

We consider concept of approximate query in RDBMS i.e. query that returns results which may differ from common (exact) query results in a way but its evaluation requires less resources. In the work we focus mostly on time and storage space aspects. We follow one of the state-of-the-art trends using synopses of data as the input of approximate query evaluation. We propose some measures of approximate query results quality. Basing on them we present steps of adaptive elaboration of synopses quality measure that should be mutually corresponding.