Munich Personal RePEc Archive

A SAS Macro for Implementing the Generalized RAS Algorithm for Constraining Matrices of Mixed Sign

Coleman, Charles (2016): A SAS Macro for Implementing the Generalized RAS Algorithm for Constraining Matrices of Mixed Sign.

This is the latest version of this item.

[img]
Preview
PDF
MPRA_paper_78182.pdf

Download (4MB) | Preview

Abstract

The problem of constraining matrices of mixed sign to controls of possibly mixed sign arises in input-output matrices in economics and net migration in demography. The recently developed Generalized RAS (GRAS) algorithm is presented to solve these problems. The GRAS algorithm produces a unique solution that minimizes an entropy-like function. The algorithm is applied to a well-known example and compared to the solution originally obtained using a generalization of the Akers-Siegel procedure.

Available Versions of this Item

UB_LMU-Logo
MPRA is a RePEc service hosted by
the Munich University Library in Germany.