CLUSTERING FACTOR ESTIMATION FOR TOTALLY CLUSTERED ATTRIBUTES

Cost models based on the clustering factor (CF) of the attributes have been proposed and shown to be attractive for block access estimation in databases, thanks to their accuracy and economy of use. While query optimizers can use the actual CFs, measured from the data, physical d esign methods and tools must rely on estimates before the data are sto red. In this paper we present a CF estimation procedure which can be a pplied to totally clustered attributes (e.g. ordered attributes). Simp le and accurate approximations of the derived formulas are also introd uced. Simulations show the accuracy of the proposed CF estimates and t he improvement in their behaviour compared to previously published est imates. Reliability for physical design of cost models based on the CF in the presence of a skewed data distribution is also discussed.