Inventories estimation by vector autoregression model

The lack and inconsistency of information on the availability and movement of inventories is forcing national accountants to look for new approaches for their reliable calculation, in addition to the commonly used commodity flow method (balance sheet method), due to inaccuracies, due to the many incoming payments. To refine the results the author proposes to use mathematic models, in particular, macroeconometric models of vector autoregressive time series given in the form of a system of simultaneous econometric equations relying on several time series with the slowdowns, lags. Taking first differences of variables in these models is suitable to achieve stationarity for initially non-stationary time series and for estimation of increases, in particular, on changes in inventories. The latter is a component of gross domestic product reflected in the capital account of the nation and behaves very unstable, due to expectations of economic agents, market conditions and possible seasonal influence. Initial stationarity of inventories time series, given a sufficiently lengthy observations, makes possible the calculation of their levels, in particular, for the balance sheet of the nation. One of the key moments in the calculation of inventories is their deflation in comparable prices to highlight the «imaginary» part of their value due to price changes during the time spent in their inventory. The article proposes to impute duration (turnover) as the length of the vector autoregression lag, implying thus the cycle time of the use of inventories. The change in the value due to price changes is proposed to rewrite in a kind of moving average model expressed via the functions of «impulse response».

векторная авторегрессия, эконометрическое моделирование, запасы материальных оборотных средств, пересчет показателя в постоянных (сопоставимых) ценах, Vector autoregression, econometric modeling, inventories, deflation in constant (comparable) prices

1. Бессонов В.А., Петроневич A.B. Сезонная корректировка как источник ложных сигналов // Экономический журнал Высшей школы экономики. 2013. Т. 17. № 4. С. 554-584.

2. Малаховская О.А., Пекарский С.Э. Исследования причинно-следственных взаимосвязей в макроэкономике: Нобелевская премия по экономике 2011 г. // Экономический журнал Высшей школы экономики. 2012. Т. 16. № 1. С. 3-30.

3. Clausen J.R., Hoffmaister A.W. Cyclical behavior of inventories and growth projections: Recent evidence from Europe and the United States // IMF Working Paper WP/10/212, 2010. URL: http://www.imf.org/external/pubs/ ft/wp/2010/wp10212.pdf (дата обращения 23.02.2016).

4. Deutsche Bundesbank. Macro-econometric multi-country model: MEMMOD. 2000. URL: https://www. bundesbank.de/Redaktion/EN/Downloads/Tasks/ Monetary_policy/economics_macro_econometric_ multi_country_model.pdf?_blob=publicationFile (дата обращения 23.02.2016).

5. Dufour A., Engle R.F. Time and the price impact of a trade // The Journal of Finance. 2000. Vol. 55. Iss. 6. P. 2467-2498. doi:10.1111/0022-1082.00297.

6. Hillier F.S., Lieberman G.J. Introduction to operations research, 8th ed. New. York: McGraw-Hill, 2005.

7. Sims C. Macroeconomics and Reality // Econometrica. 1980. Vol. 48. No. 1. P. 1-48.

8. Wu O.Q., Chen H. Optimal control and equilibrium behavior of production inventory systems // Management Science. 2010. Vol. 56. Iss. 8. P. 1362-1379.