Information content of data with respect to models.

ABSTRACT

A measure is proposed for the information content of data with respect to models. A model, defined by a set of parameter values in a mathematical framework, is considered a point in a hyperspace. The proposed measure expresses the information content of experimental data as the contribution they make, in units of information bits, in defining a model to within a desired region of the hyperspace. This measure is then normalized to conventional statistical measures of uncertainty. It is shown how the measure can be used to estimate the information of newly planned experiments and help in decisions on data collection strategies.