Scalar measures of uncertainty

In this paper we propose several scalar (single value) measures that can summarise the uncertainty in large amounts of inter-related figures such as those arising in the context of the national accounts. Such scalar measures are much easier to present and to be used than the (co)variances of all figures separately.
Many macro-economic figures, such as those arising in the context of national economic and social accounting systems, are connected by known constraints. We refer to such identities as accounting equations. The estimation of the accounting equation, most often based on a variety of sources, usually involves a reconciliation step by which the input estimates are modified to conform to the known identities. In this paper we consider the measurement of uncertainty in such reconciled estimated accounting equations and develop scalar uncertainty measures that capture both the adjustment effect as well as the relative contribution of the various input estimates to the final estimated account.