International Journal of Computational Economics and Econometrics (24 papers in press)
Investigating the Monetary and Fiscal Policy Regimes Dominance for Inflation Determination in Nigeria: A Bayesian TVP-VAR Analysis
by Olusola Oyeleke, Lukman Oyelami, Adeyemi Ogundipe
Abstract: Persistent increase in general price level has been generating policy issues between monetary and fiscal authorities in Nigeria. This study explores dominance of policy regime (monetary versus fiscal) and extends the analysis to inflation determination in Nigeria from 1981 to 2016. The study makes use of secondary data sourced from Central Bank of Nigeria (CBN) Statistical Bulletin, 2016. Stationarity properties of the variables are examined using Augmented Dicky-Fuller (ADF) and Philip-Perron (PP) unit root tests. Johansen cointegration test results show the presence of long run relationship among the variables. The study employs Bayesian Time Varying Parameter Vector Auto Regression (TVP VAR) with stochastic volatility and draws sample with Markov Chain Monte Carlo (MCMC) to generate impulse response functions. The results show that there is no definite policy regime dominating in the economy of Nigeria. The implication is that inflation problem could not be attributed to a particular policy regime. Therefore, for ease of adjustments, a definite policy regime should be allowed to prevail to achieve price stability in the economy of Nigeria.
Keywords: Bayesian TVP-VAR; fiscal policy; monetary policy; Nigeria; inflation.
The Effect of Female Employment on Saving-Investment Gap and the Role of Their Interaction in the Economic Growth
by Oznur Ozdamar, Sibel Gunduz, Eleftherios Giovanis
Abstract: A large number of countries experience negative saving-investment (S-I) gaps, which can be detrimental to economic growth. Earlier literature indicates that women save more than their male counterparts. In this study, our preliminary aim is to understand, whether female employment rates increase domestic savings that could potentially contribute positively to the S-I gaps in the low and middle-income countries. Second, we aim to investigate whether the interaction of female employment rates and S-I gap matters for economic growth. The entire analysis relies on panel data from 74 low and middle-income countries over the period 2000-2017. Various panel data techniques are applied, and they reveal similar results. The main finding of the study shows that low levels of female employment rate, and therefore inferior female earnings, are obstacles to an adequate amount of savings accumulation, necessary to close the savings-investment gap and thus, to enhance economic growth.
Keywords: Economic Growth; Female Employment Rate; Gender-Wage Gap; Low and Middle Income Countries; Panel Data Analysis; Saving-Investment Gap.
Tax Benefits Determinants and Earnings Management: Results from the Eurozone Countries
by Panagiotis Tachinakis
Abstract: Previous evidence indicates that there are considerable benefits for firms operating in tax havens, defined as countries that provide tax benefits to attract foreign capital. Using a sample of Eurozone countries along with tax haven country rankings, we examine how firms adjust their level of earnings management in response to some countries tax benefits. We also explore whether and to what extent countries different tax characteristics influence the relationship between earnings management and the existence of tax benefits. Our findings indicate that firms domiciled in countries with lower tax rates have lower levels of earnings management than companies domiciled in other European countries. However, countries with higher tax contribution rates and higher tax haven scores have lower earnings management scores. Our results suggest that firms domiciled in tax havens have interests other than just the low tax rates. In fact, the more flexible regulatory environment in these countries is a key feature that attracts firms to tax havens.
Keywords: Earnings management; tax havens; tax revenue.
A SAS Macro for Examining Stationarity Under the Presence of up to m Endogenous Structural Breaks with an Application on EU28 Agri-Food Exports
by Dimitrios Dadakas
Abstract: I present a SAS macro, that allows the examination of stationarity under the presence of up to $m$, endogenously determined, structural breaks using the methodology presented by Kapetanios (2005). The computationally intensive grid-search procedure allows researchers with minimum programming skills to easily apply the macro to the scope of their research. I demonstrate the macro using EU28 exports of agro-food products, HS categories 1 through 24. The code prepares a report of the results in PDF format.
Keywords: Endogenous Structural Breaks; Stationarity; Time Series; SAS; Macro.
A comparison of SVR and NARX in financial time series forecasting
by Engin Tas, Ayca Hatice Atli
Abstract: Machine learning techniques have become attractive due to their robustness and superiority in predicting future behavior in various areas. This paper is aimed to predict future stock prices by applying a non-linear autoregressive network with exogenous inputs (NARX) and support vector regression (SVR). For this aim, we use the daily trade data, including highest price, lowest price, closing price, and trade volume for the stocks with the highest transaction volumes from Borsa Istanbul (BIST). In order to evaluate the performance of the prediction models, various statistical measures are used. The experimental results indicate that the techniques used are quite capable of predicting the future price of a stock. Moreover, both methods are competitive with each other and have superiorities in different aspects.
Keywords: artificial learning; artificial neural networks; financial time series forecasting; nonlinear autoregressive network with exogenous inputs; support vector regression.
The App-RegMIP: an open access software for regional input-output tables estimation
by Sebastian Nicolsas Gonzalez, Carlos Adrian Romero, Maria Priscila Ramos, Pablo Augusto Negri, Matias Marino
Abstract: To extend automatic regionalisation of a national input-output (IO) matrix we developed an (online and desk version) open access software tool, the App-RegMIP, which applies location quotients methods for regional coefficients estimations (FLQ, AFLQ). By considering a national IO matrix and sectoral gross outputs of the regions of interest, this software makes it possible to compute a first approximation of regional IO matrices in an easy and tractable way. These RIO matrices are the basic inputs for regional interindustry structure analysis, as illustrated by the case study of an Argentine Province. The App-RegMIP is thus a useful tool for the process
of regional data generation and the first of its kind that is open access. Further extensions of this software could be the inclusion of other methods of regionalisation and matrices calibration methods, and the computation of multipliers and analytical indicators that can contribute to researchers studies and policy-makers decisions.
Keywords: non-survey techniques; regional input-output tables; location quotients methods; regionalisation open-access software; App-RegMIP; Argentina Province case study.
Stackelberg Secure Modeling Game Scheme for Price-Power Control in Cognitive Radio Enabled Agriculture System
by Khyati Chopra
Abstract: Cooperative communication is known to offer improvements in energy saving mechanism, spatial diversity and coverage expansion. Node Cooperation in wireless networks is also a propitious technique for enhancing the physical layer security of wireless transmission, with respect to secrecy capacity and intercept probability, in the presence of eavesdroppers. Cooperative cognitive radio (CCR) has emanated as a dynamic spectrum access technique, where the licensed spectrum which is dedicated to primary users(PUs) is concurrently accessed by the unlicensed (secondary) users. The powers of secondary users (SUs) are controlled such that the quality of service (QoS) of primary communication is not affected. Due to dynamic and broadcast nature of cognitive networks, security has become a critical issue in these networks. The smart 'Internet of Things' (IoT) based farming is capable of capturing the sensed information and then transmitting it to the user in a cooperative cognitive radio network. This device can be controlled and monitored from remote location and thus is also vulnerable to attack by an unauthorized user. In this paper, we have proposed a Stackelberg game secure model for power trading in cooperative cognitive radio network to improve the system performance and stimulate cooperation. A leader-follower scenario is set up where, the relay or leader node is trading power to source or follower node. The utilities of both source and relay are maximized and an optimal solution is obtained using convex optimization method.
Keywords: Cognitive Radio; Decode-forward relay; interceptrnprobability; Stackelberg game; Nash equilibrium.
Reservoir computing vs. neural networks in financial forecasting
by Spyros P. Georgopoulos, Panagiotis Tziatzios, Stavros G. Stavrinides, Ioannis P. Antoniades, Michael P. Hanias
Abstract: Stock market prediction techniques are a major research area, thus, extracting time-dependent patterns for the existing predictive models is of major significance. In this work, we compare forecasting performance of the nonlinear model of recurrent neural networks (RNN) in two implementations, LSTM and CNN-LSTM, to the relatively novel approach of reservoir computing (RC), and in specific, the particular class of the echo state networks (ESN). This comparison focuses on exploiting data latent dynamics, in performing efficient training and high quality predictions of the evolution of real-world financial data. Applying a multivariate scheme to a stock market index without any stationarity techniques, a definite precedence of the ESN-RC over both types of RNNs in computational efficiency as well as prediction quality, emerges. Finally, the implemented approach is friendly to the trader, since specific values of a stock market timeseries provide with a frame allowing for in time forecasting, under real-world circumstances.
Keywords: deep learning; neural networks; reservoir computing; machine learning; time series analysis; financial-economic forecasting; algorithmic comparisons.
The influence of financial and technological structure on eco-efficiency: an application of DDF bootstrapped framework in the Italian polluting industries
by Greta Falavigna, Alessandro Manello
Abstract: In this paper, we estimate efficiency scores environmental corrected for a large sample of Italian firms operating in four different polluting industrial sectors subjected to the same European normative framework. Merging economic and emission data coming from reliable public sources, we measure overall performances through the non-parametric directional distance function and in order to improve the robustness of the results, we perform an extension of the bootstrap proposed for standard efficiency scores. Results are analysed through a truncated regression after testing for the validity of separability condition between input-output space and explanatory variables as well as in light of industrial specificity. Results show that both the financial structure and the technological status of the firms have a significant explanatory power in relation to environmental corrected efficiency scores. Policy makers should carefully consider both aspects as important issues for supporting sustainable practices.
Keywords: environmental corrected efficiency; directional distance function; DDF; bootstrapping; two-stage procedure; separability conditions.
Ensemble margin resampling approach for a cost sensitive credit scoring problem
by Meryem Saidi, Nesma Settouti, Mostafa El Habib Daho, Mohammed El Amine Bechar
Abstract: In the past few years, a growing demand for credit compel banking institution to contemplate machine learning techniques as an answer to obtain decisions in a reduced time. Different decision support systems were used to detect loans defaulters from good loans. Despite good results obtained by these systems, they still face some problems such as imbalanced class and imbalanced misclassification cost problems. In this work, we propose a cost sensitive credit scoring system, based on a two-step process. The first is a resampling step which handles the imbalance data problem followed by a cost sensitive classification step that recognises potential insolvent loans red in order to reduce financial loss. A resampling algorithm called ensemble margin for imbalanced instance (EM2I) is suggested to manage imbalanced datasets in cost sensitive learning. We compare our algorithm with other techniques from the state of the art and experimental results on German credit dataset demonstrate that EM2I leads to a significant reduction of the misclassification cost.
Keywords: cost sensitive learning; imbalanced problem; ensemble margin; credit scoring.
A non-parametric estimator for stochastic volatility density
by Soufiane Ouamaliche, Awatef Sayah
Abstract: This paper aims at improving the accuracy of stochastic volatility density estimation in a high frequency setting using a simple procedure involving a combination of kernel smoothing methods namely, kernel regression and kernel density estimation. The employed data, which are 30 years worth of hourly observations, are simulated through a constant elasticity of variance-stochastic volatility (CEV-SV) model, namely the Heston model, calibrated to fit the S&P 500 Index, in the form of a two-dimensional diffusion process (Yt, Vt) such that only (Yt) is an observable coordinate. Polynomials of different degrees are then adjusted using weighted least squares to filter the observations of the variance coordinate (Vt) from a convolution structure before applying a straightforward kernel density estimation. The obtained estimates did well when compared to previous results as they have displayed a certain improvement, linked to the degree of the fitted polynomial, by reducing the value of the mean integrated squared error (MISE) criterion computed with respect to a benchmark density suggested in the literature.
Keywords: non-parametric estimation; kernel smoothing; kernel regression; kernel density estimation; convolution structure; stochastic volatility; Monte Carlo simulations.
Simulating long run structural change with a dynamic general equilibrium model
by Roberto Roson, Wolfgang Britz
Abstract: Motivated by the emerging demand for the construction of internally consistent and sufficiently detailed scenarios of long-run economic development, in this paper we present a computable general equilibrium model (G-RDEM), specifically designed for the generation of long run scenarios of economic development, featuring a non-homothetic demand system, endogenous saving rates, differentiated industrial productivity growth, interest payments on foreign debt and time-varying input-output coefficients. We illustrate how parameters of the five modules of structural change have been estimated, and we test the model by comparing its results with those obtained by a more conventional recursive dynamic computable general equilibrium model, not designed to capture structural adjustment processes. It is indeed found that the two model formulations do produce different findings, both globally and at the regional and industrial level. Our numerical tests suggest that one very important factor is the decline in the aggregate saving rates (due to higher dependency ratios in the demographic structure), which influences capital stock accumulation, investments, composition of the final demand and productivity. In terms of employment of primary resources, we detected a general pattern of decline in the primary sector, compensated by an increase in several service industries.
Keywords: computable general equilibrium models; long-run economic scenarios; structural change; economic growth.
Testing for panel cointegration in high dimensional data in the presence of cross-sectional dependency
by Rashid Mansoor, Kristofer Månsson, Pär Sjölander
Abstract: This paper introduces some new methods to test for panel cointegration in the error correction framework. These methods are proposed since the previous approaches do not perform well when the number of cross-sectional units (N) is approximately equal to the number of time periods (T). By means of Monte Carlo simulations we investigate the size and power properties when N and T increase simultaneously, i.e., N/T → c where 0 < c ≤ 1. Based on the simulated results we may recommend a test for panel cointegration in high dimensional setting with cross-sectional dependency.
Keywords: error correction model; panel cointegration; increasing dimension.
Analysing the degree of integration of the euro area: how a lack of complete markets and insufficient risk sharing raise concerns about its durability and stability
by Januj Amar Juneja
Abstract: The goal of the creation of the euro area (EA) was to bring forth a common currency and interest rate structure that would reduce risk associated with trade across its members that, over time, would lead to a convergence in the prices of financial markets containing important economic variables and an increase in integration. However, in the current study, to date, we find that the states comprising the EA suffer from incomplete integration and unequal risk sharing. Even if the EA experienced full integration and it experienced complete risk sharing, to the extent that these are theoretically feasible, some states would reap inconsequential gains in the extent of their integration and ability to share risks within the EA, while its variation in integration and risk sharing would remain quite large across member states, raising concerns about the EA's durability and stability.
Keywords: integration; euro area; risk sharing; market completeness; uncertainty modelling.
Special Issue on: Spatial Analysis and Interaction in Economics and Econometrics Data and Modelling for Sustainable Spatial Systems
A dose response evaluation of regional incentives to R&D
by Raffaele Spallone, Giovanni Cerulli
Abstract: The paper investigates the effects of regional research and development (R&D) incentives granted by the Italian regions in the period 1999-2016 on the performance of the different regional economies. We adopt a continuous treatment model that allows us to analyze the impact of the public support on a series of outcome variables. By studying the shape of the dose response function, i.e. the average treatment effects over all the possible values of the treatment levels, we are able to gauge the impact of public R&D on business performance when the level of the aid intensity changes. By this strategy, we are able to catch differences due a different policy exposure (or dose) provided at regional level. In fact, the dose-response approach employed in this study is suited when treatment is continuous, and individuals may react heterogeneously to observable confounders. The empirical analysis is carried out on a novel dataset built on purpose, which consists of a panel covering the whole amount of R&D incentives granted by the Italian regions to business activities between 1999 and 2016. We built our database using data sources made available by the Italian Ministry of Economic Development (MISE).
Keywords: State aid; evaluation of public policy; R&D incentives; cohesion.
Perspective of an exchange rate policy for global financial systems: evidence between China and ASEAN countries
by Chukiat Chaiboonsri, Satawat Wannapan, Nisit Phanthamit
Abstract: Currency rate fluctuations are essential drivers of international trade in mainland China and South East Asia, with the Chinese currency influencing deeply the economies of ASEAN countries. By employing copulas models, this paper investigates empirically currencies structural dependences. The relationships between RMB Chinese Yuan and ASEAN currencies are thus computationally analyzed. Our approach structurally classifies the flows and impulse responses activated by currency appreciation and depreciation. Additionally, agent-based simulations are carried out to depict systematical economic scenarios under currency fluctuation, thus providing suitable alerts for decision-makers when dangerous outlooks concerning trade dynamics in Indochina can take place.
Keywords: Exchange rates; Macroeconomics; Economic extreme cases; Copulas; Agent-based analysis; Monte Carlo simulation; China; ASEAN.
Transnational public research funding in Europe: exploring proximity dimensions in the ERA-NET programmes
by Antonio Zinilli, Andrea Orazio Spinello, Emanuela Reale
Abstract: This paper explores the factors that affect the decisions of policy makers at the national level for what concerns engaging in transnational joint research activities and mobilizing dedicated financial resources. The authors test whether different levels of proximity are likely to influence the emergence of similar patterns across countries in terms of participating in transnational research programmes. The research question is investigated by analyzing JoREP 2.0, a database containing data on the organisational and financial characteristics of transnational joint research programmes in Europe and the policy actors involved. Heterogeneity of socio-economic research objectives and closeness in domestic Research and Development funding and scientific performance are likely to influence the commitment of financial resources by European countries in joint research programmes, such as ERA-NETs.
Keywords: Public Research Funding; Proximity; Spatial Models; ERA-NET Programmes.
Simulating the effect of El Ni
by Edmondo Di Giuseppe, Gianfranco Giulioni, Massimiliano Pasqui
Abstract: This work analyzes the impact that the fluctuations of the large-scale atmospheric-oceanic phenomenon known as El Ni
Keywords: Computational model; Wheat international markets; Climate variability; Robust Anova regression; price cross-section distributions.
Causal statistics of structural dependence space-based trend simulations for the coalition of rice exporters: the cases of India, Thailand, and Vietnam
by Anuphak Saosaovaphak, Chukiat Chaiboonsri, Satawat Wannapan
Abstract: This paper is a contribution seeking an econometric solution for the mathematical problem known as a cooperative game. The theoretical coalition of world major rice exporters includes India, Thailand, and Vietnam. In terms of methodological processes, yearly time-series variables (2008-2018) such as the values of rice production, rice consumption, and rice exporting profits are observed. The causal model is employed to clarify three mixed approaches. The first is the structural dependent analysis based on Bayesian statistics referred to as the Bayesian Copula. The empirical results confirm that these three countries have deep structural dependences in the market. In the second method, the trends of observed variables are predicted by the Bayesian structural time-series model. The last section is the Shapley value with coalition scenarios. Optimized results causally prove that rice exporting profits are a double increment when cooperative behaviors continuously exist. Hence, the potential outcomes framework is to finally recognize the Organization of Rice Exporting Countries (OREC).
Keywords: Rice exports; Bayesian copulas; Bayesian structural time-series analysis; Shapley value; Coalition game.
The Effects of Education and Experience on Youth Employee Wages: The Case of Turkey
by Ebru Caglayan Akay, Fulden Komuryakan
Abstract: The aim of this study is to reduce the disadvantages experienced by young Turkish employees, such as age discrimination, by analysing their wage structure and the factors that could affect their earnings. This study could fill the gaps in the literature on youth employee wages in the Turkish labour force. Using the 2018 Household Budget Survey data, this study addresses five research questions, estimates the extended Mincer wage equation with robust estimators to respond to the research questions. The findings show that postgraduate and bachelors degrees have a high incremental effect on wages and the wage gaps between the degrees are wide. Each added year of experience impacts wages because employers prefer more experienced employees to avoid the cost of training them. Young female employees earn less than young male employees because of occupational segregation, motherhood penalty, and gender norms. Due to the lack of opportunities for part-time jobs in the Turkish labour force, there is a wide gap between the wages for full-time and part-time jobs. This study contributes to a better understanding of young employees' wage structure with robust-to-outliers econometric analysis and may guide to develop techniques to reduce the disadvantages for young Turkish individuals in the labour market.
Keywords: Mincer; youth labour market; wage equation; robust regression; S; MM; Turkey.
EXPLORING BREXIT IMPLICATIONS: THE IMPACT OF LONGER JOURNEY TIMES
by Bernard Fingleton
Abstract: Brexit implies longer journey times between UK and EU regions. In this paper the elasticity of trade with respect to journey time by goods vehicles is estimated, and the impact of this on employment is evaluated using a dynamic spatial panel data model. The estimator allows for the presence of endogenous and predetermined causal variables, regional interdependence, and attempts to control for common factors causing macro-economic variation over the estimation period. The estimates show that a job shortfall can be expected in both the UK and EU regions, with considerable diversity of outcome across regions.
Keywords: journey times; dynamic spatial panel model; regional employment.
Does spatial location affect business liquidations?
by Alexios Makropoulos, Charlie Weir, Xin Zhang
Abstract: Current studies in aggregate business liquidations have paid little attention to the potential importance of firms geographical (spatial) location. There is some evidence of spatial concentration of economic activity in certain geographical across Europe which crates firm interdependence. However, the literature does not currently provide evidence for the potential existence of spatial effects in business liquidations that could be influenced from business interdependence in certain geographical areas. This study investigates the potential existence of spatial effects in liquidated businesses in a sample of European countries. As such, it investigates the extent to which spatial econometrics can provide further insights into the study of aggregated business liquidations. Statistically significant spatial effects were detected in the form of SE and SD spatial models. These results confirm the existence of spatial effects in business liquidations, implying that the spatial location should be considered for modelling and policy making purposes. As such, further research is needed in this area so as to further explore the impact of the spatial aspect.
Keywords: Business failure; liquidations; Spatial effects; European countries.
Special Issue on: Computational and Statistical Modelling for Tackling the Emergence of the COVID-19 Pandemic
The management of COVID-19 epidemic: estimate of the actual infected population, impact of social distancing and directions for an efficient testing strategy. The case of Italy
by Federico Brogi, Barbara Guardabascio, Giulio Barcaroli
Abstract: This work focuses on the so called 'first wave' of COVID-19 epidemic (21 February10 April 2020) and aims at outlining a viable strategy to contain the COVID-19 spread and efficiently plan an exit from lockdown measures. It offers a model to estimate the total number of actual infected among the population at national and regional level inferring from the lethality rate, to fill the proven gap with the number of officially reported cases. The result is the reference population used to develop a forecasting exercise of new daily cases, compared to the reported ones. The eventual discrepancy is analysed in terms of compliance with the restrictive measures or to an insufficient number of tests performed. This simulation indicates that an
efficient testing policy is the main actionable measure. Furthermore, the paper
estimates the optimal number of tests to be performed at national and regional
level, in order to be able to release an increasing number of individuals from
Keywords: COVID-19; policy evaluation; scenario analysis; infected population; testing strategy; compliance; Italy.
Socio-economic and demographic factors influencing the spatial spread of COVID-19 in the USA
by Christopher F. Baum, Miguel Henry
Abstract: As the COVID-19 pandemic progressed in the USA, 'hotspots' shifted geographically over time to suburban and rural counties showing a high prevalence of the disease. We analyse population-adjusted confirmed case rates based on daily US county-level variations in COVID-19 confirmed case counts during the first several months of the pandemic (1 March 2020 through 23 May 2020) to evaluate the spatial dependence between neighbouring counties and quantify the overall spatial effect of socio-economic and demographic factors on the prevalence of COVID-19. We indeed find strong evidence of county-level socio-economic and demographic factors influencing the spatial spread such as sex, race, ethnicity, population density, pollution, health conditions, and income. The relevance of the spatial factors suggests that neighbouring counties have a significant and positive effect on the prevalence of COVID-19.
Keywords: COVID-19; coronavirus; spatial spillovers; socio-economic factors; demographics; spatial econometrics.