THE METHODS FOR RECONCILING THE PRELIMINARY QUARTERLY ESTIMATES OF PRODUCT AND INDUSTRY OUTPUTS WITH ANNUAL PRODUCTION DATA
Abstract
The aim of this article is to introduce a family of methods for reconciling the preliminary quarterly estimates of product and/or industry outputs with the corresponding annual outputs at given values of quarterly total outputs. Mathematical framework of the methods leans on generalized least squares principle, which is applied in linear vector space of output seasonal coefficients. The procedure for reconciling the quarterly and annual data on product and industry outputs is formulated as a separable programming problem with a quadratic objective function and linear constraints. The solution of this problem is obtained in analytical form. Separability of the reconciling problem allows introducing its «product» and «industry» reduced modifications. In particular, reduced modifications of the problem can serve as useful tools for balancing the incomplete sets of preliminary quarterly estimates of the product and industry outputs in order to bring them into conformity with the corresponding fragments of the annual output matrix. Simplicity of practical calculations and a very moderate need for computational resources are valid advantages of the proposed methods. In addition, the methods demonstrate a high degree of flexibility and adaptability in solving problems of reconciling the quarterly estimates of product and/or industry outputs with annual output data. High flexibility is provided by the dependence of the separable programming problem and its reduced modifications on the exogenous parameters that are allowed purposeful varying during calculation process.
About the Authors
V. I. Motorin
National Research University Higher School of Economics
Russian Federation
Russian Federation
D. D. Kenchadze
Federal State Statistics Service (Rosstat)
Russian Federation
Russian Federation
References
1. Stone R., Champernowne D.G., Meade J.E. The precision of national income estimates. Review of Economic Studies, 1942, vol. 9, no. 2, pp. 111-125.
2. Rassier D.G., Howells T.F., Empey N.R., Roesch C.E. Implementing a reconciliation and balancing model in the U.S. industry accounts. BEA working paper WP2007-04. Washington D.C., 2007. 22 р.
3. Dagum E.B., Cholette P.A. Benchmarking, temporal distribution, and reconciliation methods for time series / Lecture Notes in Statistics. Vol. 186. New York, Springer Science+Business Media, 2006. 409 p.
4. Bos F. The art and craft of compiling national accounts statistics and their implications for reliability. Review of Income and Wealth, 2009, ser. 55, no. 4, pp. 930-958.
5. Chen B. A balanced system of U.S. industry accounts and distribution of the aggregate statistical discrepancy by industry. Journal of Business & Economic Statistics, 2012, vol. 30, no. 2, pp. 202-211.
6. Taha H. Operations research: An introduction. New York and London, Macmillan Publishing Co, Inc. and Collier Macmillan Publishers, 1982 (Russ. ed.: Takha Kh. Vvedenie v issledovanie operatsii: V 2-kh kn. Kn. 2. Moscow, Mir Publ., 1985. 496 p.).
Review
For citations:
Motorin V.I., Kenchadze D.D. THE METHODS FOR RECONCILING THE PRELIMINARY QUARTERLY ESTIMATES OF PRODUCT AND INDUSTRY OUTPUTS WITH ANNUAL PRODUCTION DATA. Voprosy statistiki. 2017;1(10):3-12. (In Russ.)
Views:
358
Email this article 