Evaluation of the relative performance of RAS and cross-entropy techniques for updating input-output tables of Malaysia

• Main Authors: Saari, Mohd Yusof, Hassan, Azman, Abd Rahman, Muhammad Daaniyall, Mohamed, Azali
• Format: Article
• Language: English
• Published: Faculty of Economics & Administration, University of Malaya and Malaysian Economic Association 2014
• Online Access: http://psasir.upm.edu.my/id/eprint/37543/1/Evaluation%20of%20the%20relative%20performance%20of%20RAS%20and%20cross.pdf; http://psasir.upm.edu.my/id/eprint/37543/; http://mjes.um.edu.my/811-990
• Institution: Universiti Putra Malaysia

The growing interest in applied general equilibrium models for policy analyses increases the demand for up-to-date input-output tables. Constructing survey-based input-output tables for a recent year is costly and time-consuming. These constraints have led to the emergence of non-survey updating techniques. In this paper, the relative performance of two prominent non-survey techniques designed to update input-output tables, the RAS and cross-entropy, is compared. Results show that the cross-entropy technique is superior to the RAS regardless of the size of matrices. For both techniques, our analyses suggest that the accuracy of estimates improves with a high level of sectoral aggregation.