Econometric Analysis of Production Networks with Dominant Units
نویسندگان
چکیده
This paper considers production and price networks with unobserved common factors, and derives an exact expression for the rate at which aggregate uctuations vary with the dimension of the network. It introduces the notions of strongly and weakly dominant and non-dominant units, and shows that at most a nite number of units in the network can be strongly dominant. The pervasiveness of a network is measured by the degree of dominance of the most pervasive unit in the network, and is shown to be equivalent to the inverse of the shape parameter of the power law tted to the network outdegrees. New cross-section and panel extremum estimators for the degree of dominance of individual units in the network are proposed and their asymptotic properties investigated. Using Monte Carlo techniques, the proposed estimator is shown to have satisfactory small sample properties. An empirical application to US input-output tables spanning the period 1972 to 2007 is provided which suggests that no sector in the US economy is strongly dominant. The most dominant sector turns out to be the wholesale trade with an estimated degree of dominance ranging from 0.72 to 0.82 over the years 1972-2007. Keywords: aggregate uctuations, strongly and weakly dominant units, spatial models, outdegrees, degree of pervasiveness, power law, input-output tables, US economy JEL Classi cations: C12, C13, C23, C67, E32 We acknowledge helpful comments by Daron Acemoglu, Vasco Carvalho, Ron Smith, Martin Weidner, and participants at the Max King Conference at Monash University, the 2017 Asian Meeting of the Econometric Society, the third Vienna Workshop on High Dimensional Time Series in Macroeconomics and Finance, the fourth annual conference of the International Association for Applied Econometrics (IAAE), and seminar participants at University of Southern California. We would also like to thank Ida Johnsson for help with the compilation of input-output tables. Yang gratefully acknowledges the IAAE travel grant. Corresponding address: Department of Economics, University of Southern California, 3620 South Vermont Avenue, Kaprielian Hall 300, Los Angeles, CA 90089, USA. E-mail addresses: [email protected] (M. Hashem Pesaran), [email protected] (Cynthia Fan Yang).
منابع مشابه
Forecasting Iran’s Rice Imports during 2009-2013
In the present study Iran’s rice imports trend is forecasted, using artificial neural networks and econometric methods, during 2009 to 2013, and their results are compared. The results showed that feet forward neural network leading with less forecast error and had better performance in comparison to econometric techniques and also, other methods of neural networks, such as Recurrent networks a...
متن کاملA spatio-temporal econometric model of regional growth in Spain
In this paper, a combined cross-section and time-series econometric analysis of Spanish regional growth is presented. This analysis operates with a database where the number of cross-sectional units is small for a typical panel of data, while the time dimension is clearly dominant. First, using recent techniques in the econometric analysis of panel data (both panel unit root and panel co-integr...
متن کاملAnalysis and Comparison of Load Flow Methods for Distribution Networks Considering Distributed Generation
Conventional passive distribution networks are changing to modern active distribution networks which are not radial. Conventional load flow methods should be modified for new distribution networks analysis. In modern distribution networks distributed generation (DG) units are embedded with conventional and/or renewable resources. DG units are generally modeled as PV or PQ nodes which inject ...
متن کاملEstimation of Industrial Production Costs, Using Regression Analysis, Neural Networks or Hybrid Neural - Regression Method?
Estimation (Forecasting) of industrial production costs is one of the most important factor affecting decisions in the highly competitive markets. Thus, accuracy of the estimation is highly desirable. Hibrid Regression Neural Network is an approach proposed in this paper to obtain better fitness in comparison with Regression Analysis and the Neural Network methods. Comparing the estimated resul...
متن کاملAn Analysis of Energy Use, CO2 Emissions and Relation Between Energy Inputs and Yield of Hazelnut Production in Guilan Province of Iran
The objectives of this research were to investigate influences of energy inputs and energy forms on output levels and evaluation of CO2 emissions for hazelnut production in Guilan province of Iran. Moreover, the sensitivity analysis was done by marginal physical productivity (MPP) method for energy inputs and energy using linear regression. Initial data were collected from 120 orchar...
متن کامل