Boldyrevskii P.B.Lobachevsky State University of Nizhny Novgorod - National Research University, Nizhny Novgorod, Russian Federation bpavel2@rambler.ru
Kistanova L.A.Lobachevsky State University of Nizhny Novgorod - National Research University, Nizhny Novgorod, Russian Federation lakistanova@mail.ru
Strengthening enterprise competitiveness of the Russian industry at the current stage is possible only through the development of innovation. The main indicators of innovation activity of enterprises are the values of the shipped innovation products and cost of some technological innovation. For the effective management of innovation and development of enterprise, the issues related to the development of models of quantitative predictions and forecast scenarios to assess the determinants of innovation development are highly relevant. The present paper analyzes the dynamics and forecasting of innovation activity of industrial enterprises of the Russian Federation in the manufacture of machinery and equipment. On the basis of collected and processed statistical data for 2002-2012, we have developed mathematical-statistical models to perform a quantitative forecast of the shipped product innovation of industrial enterprises in this kind of economic activity. Forecasting models are based on a time series analysis. We are considering such methods for predicting as the trend component analysis and forecasting based on Autoregressive models. We are showing that a polynomial model is ineffective for trend prediction, for it does not provide sufficient accuracy of the forecast. The results obtained aimed at the construction and analysis of Autoregressive time series models allow us to conclude that the forecast provides sufficient accuracy of the Autoregressive model developed using the method of instrumental variables. The introduction of a new instrumental variable allows us to estimate the parameters of the regression dynamic model built by using standard methods of Econometrics. The obtained model is statistically significant and is characterized by small autocorrelation in residues (random deviations). When constructing an instrumental variable, we used time series, reflecting the dynamics of the cost of technological innovation. The proposed model prediction error does not exceed 9.5%, which determines the possibility of its use for analyzing and predicting the values of basic indicators of innovation activity of enterprises.
Keywords: innovation activity, production, machinery and equipment, dynamics model, forecast, time series
References:
Bagrinovskii K.A. Modeli i metody sovershenstvovaniya mekhanizmov innovatsionnogo razvitiya ekonomiki Rossii na osnove adaptivnogo upravleniya [Models and methods to improve the mechanisms for innovative development of Russia’s economy, based on adaptive control]. Ekonomika i matematicheskie metody – Economics and mathematical methods, 2011, vol. 47, no. 4, pp. 111–121.
Bannikov V.A. Vektornye modeli avtoregressii i korrektsii regressionnykh ostatkov [Vector models of auto-regression and correction of regression residuals]. Prikladnaya ekonometrika – Journal of applied econometrics, 2006, no. 3, pp. 96–120.
Berndt E.R. Praktika ekonometriki [Practice of Econometrics]. Moscow, Yuniti-Dana Publ., 2005, 388 p.
Boldyrevskii P.B. Osnovnye elementy sistemy upravleniya riskami promyshlennykh predpriyatii [The key elements of a risk management system of industrial enterprises]. Vestnik Nizhegorodskogo universiteta im. N.I. Lobachevskogo – Bulletin of Lobachevsky State University of Nizhny Novgorod, 2013, no. 3, pp. 31–34.
Boldyrevskii P.B., Kistanova L.A. Matematiko-statisticheskaya model’ innovatsionnoi deyatel’nosti promyshlennykh predpriyatii [A mathematical-statistical model of innovation activity of industrial enterprises]. Ekonomicheskii analiz: teoriya i praktika – Economic analysis: theory and practice, 2014, no. 15, pp. 57–64.
Boldyrevskii P.B., Kistanova L.A. Otsenka effektivnosti innovatsionnoi deyatel’nosti promyshlennykh predpriyatii [Evaluation of innovation activity of industrial enterprises]. Aktual’nye voprosy nauki – Actual problems of science, 2014, no. 12, pp. 65–69.
Borovikov V.P. STATISTICA. Iskusstvo analiza dannykh na komp’yutere: dlya professionalov [STATISTICA. The art of data analysis on the computer: for professionals]. St. Petersburg, Piter Publ., 2003, 688 p.
Borovikov V.P., Ivchenko G.I. Prognozirovanie v sisteme STATISTICA v srede Windows: osnovy teorii i intensivnaya praktika na komp’yutere [Forecasting in the STATISTICA system in Windows: the bases of theory and intensive practice on the computer]. Moscow, Finansy i statistika Publ., 2006, 367 p.
Gromova N.M., Gromova N.I. Osnovy ekonomicheskogo prognozirovaniya [Foundations of Economic Forecasting]. Available at: Link. (In Russ.)
Lyubushin N.P., Babicheva N.E., Korolev D.S. Ekonomicheskii analiz vozmozhnostei tekhnologicheskogo razvitiya Rossii (na primere nanotekhnologii) [The economic analysis of the opportunities for technological development of Russia (nanotechnology as an example)]. Ekonomicheskii analiz: teoriya i praktika – Economic analysis: theory and practice, 2012, no. 9, pp. 2–11.
Magnus Ya.R., Katyshev P.K., Peresetskii A.A. Ekonometrika: nachal’nyi kurs [Econometrics: a basic course]. Moscow, Delo Publ., 2004, 492 p.
Makarov V.L. Obzor matematicheskikh modelei s innovatsiyami [An overview of mathematical models with innovation]. Ekonomika i matematicheskie metody – Economics and mathematical methods, 2012, vol. 48, no. 2, pp. 95–107.
Pitukhin E.A., Gurtov V.A., Golubenko V.A. Modelirovanie tsiklicheskikh protsessov na rossiiskom rynke truda [A modeling of cyclic processes in the Russian labor market]. Ekonomika i matematicheskie metody – Economics and mathematical methods, 2012, vol. 48, no. 2, pp. 85–94.
Ekonometrika [Econometrics]. Moscow, Finansy i statistika Publ., 2005, 450 p.
