International Journal of Computational Economics and Econometrics (33 papers in press)
Beyond Equilibrium: Revisiting Two-Sided Markets from an Agent-Based Modeling Perspective
by Torsten Heinrich, Claudius Grabner
Abstract: Two-sided markets are an important aspect of today's economies. Yet, the attention they have received in economic theory is limited, mainly due to methodological constraints of conventional approaches: two-sided markets quickly lead to non-trivial dynamics that would require a computational approach, as analytical models quickly become intractable.
One approach to this problem is to opt for models that operate on an aggregated level, abstracting from most of the (micro-level) causes of these non-trivial dynamics. Here we revisit a well-known equilibrium model by Rochet and Tirole of two-sided markets that has taken this approach.
Analyzing the model from an agent-based perspective, however, reveals several inconsistencies and implicit assumptions of the original model.
This, together with the highly implausible assumptions that are required to make the model analytically tractable, limits its explanatory power significantly and motivates an alternative approach.
The agent-based model we propose allows us to study the phenomenon of two-sided markets in a more realistic and adequate manner:
Not only are we able to compare different decision making rules for the providers, we are also able to study situations with more than two providers.
Thus, our model represents a first step towards a more realistic and policy-relevant study of two-sided markets.
Keywords: Two-sided markets; Network externalities; Agent-based modeling; Simulation; Heuristic decision making; Reinforcement learning; Satisficing; Differential evolution; Evolutionary economics; Market structure; IT economics; Equilibrium dynamics.
Geographical dynamics of knowledge flows. Descriptive statistics on inventor network distance and patent citation graphs in the pharmaceutical industry.
by Ben Vermeulen
Abstract: In the knowledge-based geography of innovation literature, there are two opposing claims on the spatio-temporal pattern in knowledge flows over the course of a technological trajectory. The first claim is that, after the breakthrough, externalities stimulate agglomeration of specialized firms and thus cause the incremental inventions, extensions, and adaptations to take place progressively localized. The second claim is that, after the breakthrough, progressive codification and technological crystallization facilitates absorption and collaboration over greater distances. In this study, forward citation graphs of breakthrough patents are constructed and enriched with the NUTS3/ TL3 locations of the inventors. These forward citation graphs are subsequently used to study these claims and several more specific claims on co-inventor network distances and distances of groups of inventors across patent citations. Apart from obtaining support for existing claims, the study also reveals several distinct, more complex spatio-temporal patterns. Notably, it is found that, early on in technological trajectories, inventors generally collaborate mostly locally, yet cite knowledge sources found more remotely. Later on in technological trajectories, inventors collaborate over greater distances, yet cite more local knowledge sources. Conclusively, there is progressive globalization of inventor networks, whereby knowledge sources are used increasingly locally in follow-up inventions.
Keywords: inventor network; forward citation graph; patent analysis; geographical dynamics; spatial analysis; knowledge-based; geography of innovation; descriptive statistics.
Gender dimension of migration decisions in Ghana: The reinforcing role of anticipated welfare of climatic effect
by Franklin Amuakwa-Mensah, Victoria N. Sam, Evelyne Nyathira Kihiu
Abstract: The concept of migration has been a male phenomenon in time past, however, there has been a change in events as females are gradually gaining dominance in migration patterns in recent times. Using nationwide survey data this paper investigates the determinants of internal migration decisions for males and females in Ghana. We examined whether there is any significant differences in how climate elements together with anticipated welfare gains and socio-economic factors explain internal migration decision of males and females. We find some variations in the determinants of migration decisions for males and female, though these decisions are significantly affected by anticipated welfare gain, socio-economic factors and climate conditions. We observed that females respond more to climate or environmental elements than males. Moreover, the effect of climate on migration decisions for both males and females is reinforced by anticipated welfare gain.
Keywords: Climate; environment; males; females; migration; Heckman two-stage; Ghana.
Insurance risk capital and risk aggregation: Bivariate copula approach
by Hanene Mejdoub, Mounira BEN ARAB
Abstract: The current paper discusses the risk aggregation issue using copula theory in the sphere of the insurance industry. In this context, a flexible modelling of the dependence structure for non-life insurance risks is considered. The aim of the modelling is to assess the impact of dependence structure among losses on the total risk capital estimation measured by the Value-at-Risk. Using numerical illustrations based on a Tunisian insurance company, we use first various copula families that can capture the dependencies across losses that are derived from four lines of business. To obtain the appropriate bivariate copula, we perform a goodness-of-fit analysis. Then, based on the Monte-Carlo simulation, the total risk capital is deduced by applying the Value at risk on the aggregate loss distributions. We also conduct a comparative analysis between the various types of the copulas. Our findings reveal that there is a regular impact on the capital requirement estimation indicating that a static approach ignoring the real dependencies between different risks can systematically lead to an overestimation of the total capital requirement.
Keywords: Non-life insurance; Risk aggregation; Value-at-Risk; Dependence structure; Bivariate Copulas; Monte-Carlo Simulation.
Research Note: Futures Hedging with Stochastic Volatility: A New Method
by Moawia Alghalith, Christos Floros
Abstract: The aim of this paper is to present a continuous-time dynamic model of futures hedging. In particular, we extend the theoretical and empirical literature (e.g. Alghalith, 2016; Alghalith et al., 2015; and Corsi et al., 2008) in several important ways. First, we present a theory-based model. A significant empirical contribution is that we do not need data for the basis risk or the spot price. To the best of our knowledge, this is the first paper to assume that the volatility of futures price is stochastic and thus to estimate the volatility of volatility of futures price. Using daily futures data from the S&P500 index, we calculate an average daily volatility as well as the volatility of volatility of futures prices. We recommend that the managers of the futures market should report the stochastic volatility of the futures price (and its volatility), in addition to the traditional volatility.
Keywords: stochastic volatility; volatility of volatility; futures; hedging.
Earnings Management to Avoid Losses and Earnings Declines in Croatia
by Stavros Degiannakis, George Giannopoulos, Salma Ibrahim, Ivana Rozic
Abstract: This paper provides empirical evidence that Croatian companies manage reported earnings to avoid losses and earnings declines. Specifically, we find that the cross-sectional distribution of scaled earnings and changes in earnings show high frequencies of small positive earnings and small increases in earnings while the frequencies of small losses and small decreases in earnings are less frequent. Furthermore, we demonstrate that these discontinuities are likely due to discretionary accruals. We examine the frequency distribution of reported earnings after removing discretionary accruals and find that the cross sectional distributions of non-discretionary scaled earnings shows lower frequencies of small positive earnings and higher frequencies of small negative earnings. Additionally, the cross sectional distribution of non-discretionary change in earnings demonstrates mixed frequencies of non-discretionary changes in earnings. Overall, this paper adds new empirical evidence to the benchmark-beating literature by demonstrating international evidence of earnings management around zero earnings and zero earnings changes benchmarks.
Keywords: Earnings management; Earnings Declines; Earnings Losses; Discretionary Accruals; Earnings frequency distribution.
Depth, tightness, and resiliency as market liquidity dimensions: evidence from the Polish stock market
by Joanna Olbrys, Michal Mursztyn
Abstract: Liquidity in a financial market is not a one-dimensional variable but it includes several dimensions. The main aim of the paper is an empirical analysis of market liquidity dimensions on the Warsaw Stock Exchange (WSE). We investigate market depth, market tightness, and market resiliency for fifty-three WSE-listed companies divided into three size groups. The high-frequency data covers the period from January 3, 2005 to June 30, 2015. The additional goal is a robustness analysis of the obtained results with respect to the whole sample period and three adjacent subsamples, each of equal size: pre-crisis, crisis, and post-crisis periods. Order ratio (OR) is employed as a proxy of market depth. Market tightness is approximated by using relative spread (RS). Market resiliency is estimated by utilizing realized spread (RealS) which is a temporary component of bid/ask effective spread. As we expected, the empirical results indicate that OR values do not depend on a firm size, while RS estimations are slightly higher for small companies. RealS proxy values are positive for almost all stocks, except for isolated cases. Moreover, the results turn out to be robust to the choice of the sample for all groups of assets.
Keywords: dimensions of market liquidity; market depth; market tightness; market resiliency; Global Financial Crisis; Polish stock market.
Stein-Rule Estimation in Genetic Carrier Testing
by Tong Zeng, Carter Hill
Abstract: The random parameters logit (RPL) model is a generalization of the conditional logit model for multinomial choices. It has become popular in many fields, such as health economics. In the RPL model, the parameters are estimated with the use of simulation to approximate the integral of the likelihood over the density of the random coefficients because the choice probability in the RPL model involves a multi-dimensional integral which does not have closed form solution. When the random coefficients are correlated to each other, the maximization of the simulated likelihood function becomes more difficult and the estimated parameters have big variance. To reduce the estimation risk of the RPL model estimators when the random coefficients are correlated, we explore the properties of a Stein-like shrinkage estimator that combines the fully correlated and uncorrelated RPL model estimators. The mean squared error (MSE) is used as the risk criterion to compare the efficiency of positive-part Stein-like estimators to the efficiency of pretest and fully correlated random parameters logit (FCRPL) model estimators. The results of our Monte Carlo experiments show that the positive-part Stein-like estimator provides smaller MSE than the pretest estimator in the FCRPL model. Both of them outperform the FCRPL model estimator. The Monte Carlo mean estimates of direct elasticity with pretest and positive-part Stein-like estimates are closer to the true value and have smaller standard errors than those with FCRPL model estimates. With genetic carrier testing data, using shrinkage estimates with higher shrinkage constant improve the percentages of correct predicted choices by 2% and 10% with two different samples compared to the results with FCRPL model estimates. Most of the mean estimates of elasticity based on the FCRPL model estimates are larger in magnitude than those with uncorrelated RPL model estimates.
Keywords: Pretest Estimator; Positive-part Stein-like Estimator; Likelihood Ratio Test; Random Parameters Logit Model; Genetic Carrier Testing.
Efficiency in Banking: Does the Choice of Inputs and Outputs Matter?
by Christos Floros, Constantin Zopounidis, Christos Lemonakis, Alexandros Garefalakis
Abstract: This paper examines banking efficiency using recent data from PIGS countries (i.e.: Portugal, Italy, Greece and Spain) which suffer from debt problems. We employ a 2-stage approach based on the effect of several items of balance sheets on cash flows and DEA analysis. More specifically, we extend previous studies by giving attention to the deposit dilemma. The reported results show that the choice of inputs and outputs does matter in the case of European banking efficiency. Although the role of deposits is controversial, we find that deposits may be an output variable, due to liquidity issues that play a major role in the efficiency of PIGS banking sector. We also report that the DEA model with deposits as an output variable generates efficiency scores that fall between periods. These results are helpful to bank managers and financial analysts dealing with efficiency modelling.
Keywords: PIGS; Banking sector; Efficiency; Deposits dilemma; 2-stage approach; Cash
flows; DEA; regression.
Multi-period Mean-variance Portfolio Selection with Practical Constraints Using Heuristic Genetic Algorithms
by Yao-Tsung Chen, Hao-Qun Yang
Abstract: Since Markowitz proposed the meanvariance (MV) formulation in 1952, it has been used to configure various portfolio selection problems. However Markowitzs solution is only for a single period. Multi-period portfolio selection problems have been studied for a long time but most solutions depend on various forms of utility function, which are unfamiliar to general investors. Some works have formulated the problems as MV models and solved them analytically in closed form subject to certain assumptions. Unlike analytical solutions, genetic algorithms (GA) are more flexible because they can solve problems without restrictive assumptions.
The purpose of this paper is to formulate multi-period portfolio selection problems as MV models and solve them by GA. To illustrate the generality of our algorithm, we implement a program by Microsoft Visual Studio to solve a multi-period portfolio selection problem for which there exists no general analytical solution.
Keywords: Multi-period portfolio selection; Mean-variance formulation; Genetic algorithm; Transaction costs.
Using singular spectrum analysis for inference on seasonal time series with seasonal unit roots
by Dimitrios Thomalos, Hossein Hassani
Abstract: The problem of optimal linear filtering, smoothing and trend extraction for m-period differences of processes with a unit root is studied. Such processes arise naturally in economics and finance, in the form of rates of change (price inflation, economic growth, financial returns) and finding an appropriate smoother is thus of immediate practical interest. The filter and resulting smoother are based on the methodology of Singular Spectrum Analysis (SSA). An explicit representation for the asymptotic decomposition of the covariance matrix is obtained. The structure of the impulse and frequency response functions indicates that the optimal filter has a permanent" and a transitory component", with the corresponding smoother being the sum of two such components. Moreover, a particular form for the extrapolation coefficients that can be used in out-of-sample prediction is proposed. In addition, an explicit representation for the filtering weights in the context of SSA for an arbitrary covariance matrix is derived. This result allows one to examine the specific effects of smoothing in any situation. The theoretical results are illustrated using different data sets, namely U.S. inflation and real GDP growth.
Keywords: Core inflation; Business cycles; Differences; Euro; Linear filtering; Trend extraction and prediction; Unit root.
Bias decomposition in the Value at Risk calculation by a GARCH(1,1)
by Gholam Reza K. Haddad
Abstract: The recent researches show that Value at Risk estimations are biased and is calculated conservatively. Bao and Ullah (2004) proved the bias of an ARCH(1) model for VaR can be decomposed in to two parts: bias due to return misspecification distributional assumption for GARCH(1,1) (Bias1) and bias due to estimation error (Bias2). Using quasi maximum likelihood estimation method this paper intends to find an analytical framework for the two source of biases. We generate returns from Normal and t-student distributions, then estimate the GARCH(1,1) under Normal and t-student assumptions. Our findings reveal that Bias1 equals to zero for the Normal likelihood function, but Bias2 0. Also, Bias1 and Bias2 are not zero for the t-student likelihood function as analytically were expected. However all the biases become modest, when the number of observations and degree of freedom is large.
Keywords: Value-at-Risk; GARCH(1,1); Second-order bias.
Performance Evaluation of the Bayesian and classical Value at Risk models with circuit breakers set up
by Gholam Reza K. Haddad
Abstract: Circuit breakers, like price limits and trading suspensions, are used to reduce price volatility in security markets. When returns hit price limits or missed, observed returns deviate from equilibrium returns. This creates a challenge for predicting stock returns and modeling Value at Risk (VaR). In Tehran Stock Exchange (TSE), the circuit breakers are applied to control for the excess price volatilities. We extend Weis (2002) model, in the framework of Bayesian Censored and Missing-GARCH approach, to estimate VaR for Iran Khodro Company (IKCO) share in TSE. Using daily data for the period of June 2006 to June 2016, we show that the Censored and missing- GARCH model with t-student distribution outperforms. Kullback-Leibler (KLIC), Kupic (1995) test and Lopez score (1998) outcomes show that estimated VaR by Censored and missing- GARCH model with t-student distribution is of the most accuracy among all other classical and Bayesian estimation models.
Keywords: Circuit Breakers; Censored and Missing–GARCH; Bayesian estimation; Value at Risk; Ranking Models.
A robust generalised maximum entropy estimator for ill-posed estimation problems
by Graeme J. Doole
Abstract: The generalised maximum entropy (GME) estimator provides a flexible means of information recovery from ill-posed estimation problems. However, coefficient estimates are sensitive to the exogenous support bounds defined for coefficient and error terms. This paper describes a new estimator that identifies informative support bounds, prior to the implementation of GME regression. These bounds are estimated using interval-valued mathematical programming in a way that is data-based, replicable, and robust. The superiority of the new estimator over various alternatives is demonstrated with a series of non-trivial Monte Carlo simulations involving different degrees of multicollinearity, sample sizes, and error structures.
Keywords: maximum entropy; support bounds; ill-posed problems; multicollinearity; low sample size; interval-valued optimisation.
The model confidence set package for R
by Mauro Bernardi, Leopoldo Catania
Abstract: This paper presents the R package MCS which implements the model confidence set (MCS) procedure for model comparison. The MCS procedure consists on a sequence of tests which permits to build a set of 'superior' models, where the null hypothesis of equal predictive ability (EPA) is not rejected at a certain confidence level. The EPA statistic test is calculated for an arbitrary loss function, meaning that we could test models on various aspects, such as for example, punctual forecasts and density evaluation. The relevance of the package is shown using an example which aims at illustrating in details the use of the provided functions. The example compares the ability of different models belonging to the generalised autoregressive conditional heteroscedasticity (GARCH) family to predict large financial losses. Codes for reproducibility purposes are also reported.
Keywords: MCS; model confidence set; model choice; R; VaR; value-at-risk.
Testing the validity of instruments in an exactly identified equation
by Marco Ventura
Abstract: Whenever the number of instruments equals the number of endogenous variables testing the validity of the instruments is not a feasible task. Based on recent econometric developments (Lewbel, 2012), this paper aims at spreading among applied economists and econometricians an empirical strategy to overcome this setback, thus sidestepping the exact identification problem.
Keywords: instrumental variables; exact identification; over identifying test; Hansen-Sargan test; endogeneity.
Revisiting Kelly's version of the Herfindahl-Hirschman index
by George G. Djolov
Abstract: This communication looks at Kelly's proposed formulation of the Herfindahl-Hirschman index (HHI), which has received some attention in the economic and management fields as a promising method to improve the measurement of market concentration by supposedly taking the skewness of market shares into account in the course of the index's computation. It is found that this is not the case, and suggestions are made as to how the formulation could be aligned to its intended aim as originally proposed.
Keywords: HHI; Herfindahl-Hirschman index; relative variability.
Designing Kenya's 'first generation' revenue allocation among counties formula with imperfect data: an application of response surface methodology
by Moses Muse Sichei
Abstract: This paper investigates the design of Kenya's 'first generation' formula for sharing of revenue among 47 counties in the face of imperfect data and highly politicised issue of historical injustices in the past fiscal dispensation of a centralised system of government. We show that with limited quality data at subnational level, an innovative loss function in a response surface methodology offers an appropriate platform to generate initial weights of fiscal need factors that not only ensure redistributive justice and equity but are also perceived to be objective and fair by different political interest groups.
Keywords: revenue allocation formula; fiscal decentralisation; intergovernmental fiscal transfer system; response surface methodology; RSM; county governments; simulation; Kenya.
Assessment of R&D and its impact on Indian manufacturing industries
by Chandrima Sikdar, Kakali Mukhopadhyay
Abstract: An important source of productivity growth, technological change and hence increased welfare of a country is Research and Development (R&D). Thus, it is absolutely important to develop a country's R&D sector. However, developing countries have traditionally relied largely on import of technologies from developed countries, rather than domestic R&D for driving their technological change. India too has been no exception. But, like any other developing country, India too needs to make continuous investment either to adopt foreign technology or to develop its own capacities via R&D activities. Presently, India's R&D expenditure is merely 2.1% of total global expenditure. Against this backdrop, the present study computes elasticity of industry-level TPF with respect to R&D content of intermediates, both domestic and foreign, for industries in India. The results show that R&D stocks embodied in intermediates have contributed to productivity growth in these industries. Particularly, noteworthy is this elasticity for low-R&D industries, like, processed food, textile and wearing apparels, motor vehicles etc.
Keywords: domestic R&D; foreign R&D; international integration; TPF; total factor productivity; India; industry; input-output; intermediate inputs.
Special Issue on: ICOAE2015 Applied Economics
Reconsidering the relationship between foreign direct investment and growth
by Carlos Encinas-Ferrer, Eddie Villegas-Zermeño
Abstract: It has been assumed that foreign direct investment (FDI) is a variable that explains economic growth (EG). As investment (I) is the dynamic element of gross domestic product (GDP), therefore, FDI, as part of total investment, should be also the independent variable and GDP growth the dependent one. However, many studies in many countries have shown the contrary, there is not such a causal relationship between FDI and GDP. In our investigation, we include the study of the cases of Mexico, China, Brazil and the Republic of Korea. It is our hypothesis that there is not a causal relationship between FDI, as the independent variable, and GDP grow as the dependent one in the selected countries and that this is in part because FDI is a small proportion of total (national and foreign) direct investment and so its impact is reduced.
Keywords: FDI; foreign direct investment; GDP; gross domestic product; economic growth; gross fixed capital formation.
Special Issue on: Dynamics of and on Networks
Growth and collapse: An agent-based banking model of endogenous leverage cycles and financial contagion
by Robert De Caux, Frank McGroarty, Markus Brede
Abstract: We create an agent-based banking model that allows the simulation
of leverage cycles and financial contagion. Banks within our model adapt their
investment strategies in an evolutionary manner according to the success of their
competitors, creating an endogenous interbank loan network and a dynamic asset
market as they try to maximise profit by adjusting their leverage. The system
exhibits periods of slow risk growth and fast insolvency cascades, allowing us to
assess both the size and frequency of those cascades over a long time-frame.
We demonstrate that banks endogenise systemic risk into their leverage
behaviour when the asset market is subject to either low or high levels of volatility, but are less successful for medium volatility when the number of bank insolvencies is maximised. We also show that in a low volatility environment, banks are more susceptible to systemic contagion. While the majority of insolvencies occur
through the asset side of the balance sheet due to fire sales causing a rapid
depreciation in the asset price, failures through the liability side of the balance
sheet tend to be correlated, acting as an amplification mechanism to create far
more serious cascades.
By creating realistic cycles of growth and collapse, the model provides a
suitable framework for performing further policy tests.
Keywords: financial contagion; agent-based model; bank insolvency; evolutionary game theory; simulation; networks.
Structural Characteristics of Knowledge Exchange in Innovation Networks
by Michael Rothgang, Bernhard Lageman
Abstract: While there is a large pool of assured knowledge about various general dimensions of the structure and dynamics of innovation networks, there are several basic structural features that deserve more attention in future network research. Our contribution concentrates on three key structural characteristics: (i) the type of actors, (ii) contexts and (inter-) organiza-tional environments of networks and (iii) modes and contents of knowledge exchange. We discuss the role of these structural characteristics by using research material from an ac-companying evaluation of the German Leading-Edge Clusters Competition. Major results are: Innovation network actors present themselves in a highly heterogeneous manner; the relevant spectrum stretches from highly complex organizations to single individuals. Net-works are embedded in different sectoral, organizational and situational contexts. In many cases, even defining the boundaries of the relevant network is a challenge for innovation researchers. Knowledge exchange flows through different channels, and can be seen as a context-dependent combination of formal and tacit elements, as well as an interplay of both (relative) openness and restraint between the acting individuals and organizations.
Keywords: Innovation Networks; Knowledge Exchange; Cluster Organization; Cluster Policy.
Innovation cooperation in East and West Germany: A study on regional and technological impact
by Uwe Cantner, Alexander Giebler, Jutta Günther, Maria Kristalova, Andreas Meder
Abstract: In this paper we investigate the impact of regional and technological innovation systems on innovation cooperation. We develop an indicator applicable to regions, which demonstrates the relative regional impact on innovation cooperation. Applying this method to German patent data, we find that regional differences in the degree of innovation cooperation do not only depend on the technology structure of a region but also on specific regional effects. High-tech oriented regions, whether east or west, are not automatically highly cooperative regions. East German regions have experienced a dynamic development of innovation cooperation since re-unification in 1990. Their cooperation intensity remains higher than in West German regions.
Keywords: regional innovation system; technological innovation system; innovation cooperation; Germany.
Knowledge diffusion in formal networks The roles of degree distribution and cognitive distance
by Kristina Bogner, Matthias Mueller, Michael Schlaile
Abstract: Social networks provide a natural infrastructure for knowledge creation and exchange. In this paper we study the effects of a skewed degree distribution within formal networks on knowledge exchange and diffusion processes. To investigate how the structure of networks affects diffusion performance, we use an agent-based simulation model of four theoretical networks as well as an empirical network. Our results indicate an interesting effect: neither path length nor clustering coefficient are the decisive factors determining diffusion performance but the skewness of the link distribution is. Building on the concept of cognitive distance, our model shows that even in networks where knowledge can diffuse freely, poorly connected nodes are excluded from a joint learning in networks.
Keywords: agent-based simulation; cognitive distance; degree distribution; direct project funding; Foerderkatalog; German energy sector; innovation networks; knowledge diffusion; publicly funded R&D projects; random networks; scale-free networks; simulation of empirical networks; skewness; small-world networks.
Special Issue on: Coping with Uncertainty in Complex Socio-Economic Systems
Technology Diffusion of Industry 4.0: An Agent-Based Approach
by Martin Prause, Christina Gunther
Abstract: Governmental interventions, such as public policies and programs, play a vital role in innovation diffusion, particularly if the application area is heterogeneous, like the German federal high-tech approach of Industry 4.0. Interventions can thus inhibit market failure and negative externalities or disseminate the technology and promote positive externalities.
To analyze the impact of governmental intervention, considering the particularities of the Industry 4.0 approach, an agent-based model is proposed, particularly to test the sensitivity of Industry 4.0 innovation diffusion speed and degree due to interventions such as promotion, educational support, technology networks (hubs), technology standardization, and financial aid among manufacturing SMEs in Germany.
This article describes a conceptual model structured along the overview, design concept, and details framework. Grounding and calibration of input parameters and agent behavior are based on firm characteristics and adoption determinants (technology-organization-environment model) from survey data and Industry 4.0 case studies.
Keywords: Agent-based Model; Industry 4.0; Innovation Diffusion; SME; Technology Adoption.
Forecasting Inflation in Tunisia during Instability: Using Dynamic Factors Model
A two-step based procedure based on Kalman Fitler
by AMMOURI BILEL, TOUMI HASSEN, Fakhri ISSAOUI, ZITOUNA HABIB
Abstract: This work presents a forecasting inflation model using a monthly database. Conventional models that forecast inflation use a few macroeconomic variables. In the context of globalization and dependent economic world, models have to take into account a large amount of information. This model is the goal of recent research in various industrialized countries as well as developing ones. With the Dynamic Factors Model (DFM), the forecast values are closer to the actual inflation than those obtained from the conventional models in the short term. In our research, we devise the inflation into free and administered inflation and test the performance of the DFM under instability (before and after the revolution) in different types of inflation and trend inflation, namely administered and free inflation. Knowing that periods of instability are simultaneously the period of price liberalization of basic goods (2008) and the post-revolution period (2011-2017). We have found that the DFM with an instability factor leads to substantial forecasting improvements over the DFM without an instability factor in the period after the revolution.
Keywords: Inflation forecasting; PCA; VAR; Dynamic Factors Model; Kalman Filter; Space-state; Instability factor.
Measuring Uncertainties: a Theoretical Approach
by Carolina Facioni, Isabella Corazziari, Filomena Maggino
Abstract: When our aim is to draw the possible developments of future events,
we are faced with a practical obstacle. Indeed, we cannot have any empirical
experience of the future. Have we, therefore, to be inferred that forecasting,
exploring future or, better: exploring futures, or anticipating futures have not to
be considered activities of a scientific kind? Answer to such a difficult question
requires a multidisciplinary approach, where statistical models, methodology of
social science and of course statistics and sociology as a whole are enhanced
in their ability to express the change and sometimes the risk that the change
itself implies. A great help in understanding complexity, and trends, comes
from a method for multi-way data, based on the joint application of a factorial
analysis and regression over time, called dynamic factor analysis (DFA)
Keywords: uncertainty measure; futures studies; DFA; dynamic factor
Career mobility of PhD holders in Social Sciences and Humanities: evidences from the POCARIM project
by Lucio Morettini, Emilia Primeri, Emanuela Reale, Antonio Zinilli
Abstract: The paper aims at investigating factors that could affect the likelihood of changing job of PhD holders in the fields of social sciences and humanities (SSH). We use data collected through a survey developed within the POCARIM project (funded by the EC under the EUFP7) in order to analyse variations in PhDs\' career paths in a longitudinal dimension: we consider the career of each agent as a whole and investigate what elements related to individual features can influence careers entropy in term of changes of sector and/or country.
Keywords: Career mobility; PhD; Job market; Higher education; Career paths.
Do the Flexible Employment Arrangements Increase Job Satisfaction and Employee Loyalty? Evidence from Bayesian Networks and Instrumental Variables
by Eleftherios Giovanis
Abstract: This study explores the relationship between job satisfaction, employee loyalty and two types of flexible employment arrangements; teleworking and flexible timing. The analysis relies on data derived by the Workplace Employee Relations Survey (WERS) in 2004 and 2011. We apply the propensity score matching approach and least squares regressions. Furthermore, we employ the Bayesian Networks (BN) and Directed Acyclic Graphs (DAGs) to confirm the causality between employment types explored and the outcomes of interest. Additionally, we propose an instrumental variables (IV) approach based on the BN framework. The results support that a positive causal effect from these employment arrangements on job satisfaction and employee loyalty is present.
Keywords: Bayesian Networks; Directed Acyclic Graphs; Employee Loyalty; Employment Arrangements; Flexible Timing; Job Satisfaction; Teleworking; Workplace Employment Relations Survey.
On the Validity of Exclusion Restrictions in the Structural Multivariate Framework: a Monte Carlo Simulation
by Talel Boufateh
Abstract: This paper aims to examine the validity of identifying restrictions used in the Structural multivariate models. Whether we are under short-term identification approach and / or long term identification one, the scheme adopted implies the imposition of additional assumptions which usually take the form as exclusion restrictions. We believe however, that the value of a restriction is not necessarily equal to zero even if it expresses the lack of impact of a shock on a variable. We think that this lack of impact may reflect an effect asymptotically equal to zero and that the little nuance could be amplified with the model dynamics and affect the structural analysis. We have chosen to study this problem by using a Monte Carlo simulation and to examine the consequences of slipping of the identification restriction value. The results that emerge from this work confirm the sensitivity of variables' responses to change, even the slightest it may be, in the value of identification restrictions. Whatever the strength and elegance of the theory and the economic reasoning from which emanate the exclusion restrictions, precision measurements should be considered.
Keywords: Exclusion restrictions; SVAR approach; Monte Carlo Simulation.
Special Issue on: ICOAE2016 Applied Economics
Causality among CO2 Emissions, Energy Consumption and Economic Growth in Italy.
by Pavlos Stamatiou, Nikolaos Dritsakis
Abstract: The aim of this paper is to investigate the relationship between CO2 emissions (carbon dioxide emissions), energy consumption and economic growth in Italy, using annual data covering the period 1960-2011. The unit root tests results indicated that the variables are not stationary in levels but in their first differences. Subsequently, the Johansen cointegration test showed that there is a cointegrated vector between the examined variables. The Vector Error Correction Model (VECM) is used in order to find the causality relations among the variables. The empirical results of the study revealed that both in the short and long run there is a strong unidirectional causality relation between economic growth and CO2 emissions with direction from economic growth to CO2 emissions. Finally, the impulse response functions indicated that a reduction in CO2 emissions has a positive effect on energy consumption, while it causes a decrease in economic growth.
Keywords: Carbon emissions; Energy consumption; Economic Growth; Cointegration Test; Vector Error Correction; Causality; Variance Decomposition; Impulse response analysis; Italy.
The Public Sector Wage Premium Puzzle
by Yi Wang, Peng Zhou
Abstract: This paper investigates the public sector wage premium in the UK over the first decade of the 21st century using both econometric and economic modelling methods. A comprehensive literature review is conducted to summarise the four popular types of methods adopted by the traditional microeconometric studies. Application of these methods results in an estimated public sector wage premium equal to 6.5%. Indirect inference is then introduced as a new method of testing and estimating a microfounded economic model. All four types of econometric methods can be used as auxiliary models to summarise the data features, based on which the distance between the actual data and the model-simulated data is assessed. The selection bias can also be tested in a straightforward way under indirect inference.
Keywords: Public Sector Wage Premium; Microfoundation; Propensity Score Matching; Indirect Inference.
Modelling Agricultural Risk in a Large Scale Positive Mathematical Programming Model
by Ivan Arribas, Kamel Louhichi, Angel Perni, Jose Vila, Sergio Gomez-y-Paloma
Abstract: Mathematical programming has been extensively used to account for risk in farmers' decision making. The recent development of the Positive Mathematical Programming (PMP) has renewed the need to incorporate risk in a more robust and flexible way. Most of the existing PMP-risk models have been tested at farm-type level and for a very limited sample of farms. This paper presents and tests a novel methodology for modelling risk at individual farm level in a large scale model, called IFM-CAP (Individual Farm Model for Common Agricultural Policy analysis). Results show a clear trade-off between including and excluding the risk specification. Albeit both alternatives provide very close estimates, simulation results shows that the explicit inclusion of risk in the model allows isolating risk effects on farmer behaviour. However, this specification increases three times the computation time required for estimation.
Keywords: agriculture; positive mathematical programming; risk and uncertainty; expected utility; Highest Posterior Density; European Common Agricultural Policy.