Alternative general method of moments estimators in dynamic panel data models

This paper focuses on the estimation of fiscal response functions for advanced economies and on the performance of alternative specifications of the Generalized Method of Moments (GMM) estimator for the rule’s parameters. We first estimate the parameters on simulated data through Monte Carlo experiments; we then run an empirical test on data for the European Monetary Union (EMU). We estimate both the Cyclicallyadjusted primary balance (CAPB) and the Primary balance (PB) models, and check the robustness of the estimates to different specifications of the GMM estimator and to alternative settings of the parameters. We also compare alternative instrument reduction strategies in a context where several endogenous variables enter the model. We find that the system GMM estimator is the best-performing in this framework and the high instrument count comes out not to be problematic. We also make the algebraic links between the parameters in the CAPB and in the PB models explicit, suggesting an effective strategy to estimate the discretionary fiscal response from the coefficients of the PB model. In the empirical application on a dataset for EMU Countries, we find that the evidence of a-cyclicality of discretionary policies is robust to all the specifications of the GMM estimator.

Few estimation methods were discussed to handle the missing data problem in the panel data models. However, in the panel vector autoregressive (PVAR) model, there is no estimator to handle this problem. The traditional treatment in the case of incomplete data is to use the generalized method of moment (GMM) estimation based on only available data without imputation of the missing data. Therefore, this paper introduces a new GMM estimation for the PVAR model in case of incomplete data based on the mean imputation. Moreover, we make a Monte Carlo simulation study to study the efficiency of the proposed estimator. We compare between two GMM estimators based on the mean squared error (MSE) and relative bias (RB) criteria. The first is the GMM estimation based on the list-wise (LW) and the second is the GMM estimation using the mean imputation (MI) at multi-missing levels. The results showed that the MI estimator provides more efficiency than the LW estimator.

PurposeThis study aims to examine the effects of institutions on private investment (PI) using panel data analysis, where the sample countries consist of 100 countries around the world and the time period is covering from 2007 to 2016. The system generalized method of moments (GMM) estimator, introduced by Arellano and Bond (1991) and further developed by Blundell and Bond (1998) is used to analyze the data sets.Design/methodology/approachThis study uses the panel data approach to estimate the empirical model due to the panel nature of the data. In particular, due to the presence of lagged dependent variables and the ability to capture individual country-specific effects, the system GMM estimator, introduced by Arellano and Bond (1991) and further developed by Blundell and Bond (1998), is adopted to analyze the roles of institutions in PI. The system GMM is developed specifically to solve the problems of weak instruments and persistency (Blundell and Bond, 1998). Jointly, they suggest to adopt additional moment conditions where lagged difference of the dependent variable is orthogonal to the level form of the disturbances. The system GMM estimator is able to combine the moment conditions for the different models, as well as the level model, thereby (is capable of) generate consistent and efficient parameters. Due to the dynamic nature of the data, this study uses one-step and two-step system GMM to investigate the roles of institutions in PI.FindingsThe empirical results based on the two-step system GMM demonstrate that the quality of institutions plays an important role in stimulating PI. The finding is reinforced by the analysis of the institutional sub-components’ effects on PI.Originality/valueThis study is unique as its measurement of institutions is multi-dimensional (including law and order, rules and regulation, government stability, bureaucratic quality, control of corruption, socio-economic condition, etc.), and hence are more comprehensive. Second, it is different than the previous studies as its sample of countries includes both democracies and non-democracies, as well as both developed and non-developed economies in which policy implications are widely acceptable. Third, this study contributes to the policymakers especially those in the debt-ridden economies where governments are budget-tightening (limited capacity for public investment), as to which practical direction should be focused on so as to attract PI and eventually sustainable growth can take place.

An alternative two-step generalized method of moments estimator based on a reduced form model

In this paper we consider estimation of the autoregressive error components model. When the autoregressive parameter is moderately large and the number of time series observations is moderately small, the usual Generalised Methods of Moments (GMM) estimator obtained after first differencing has been found to be poorly behaved. Here we consider alternative linear estimators that are designed to improve the properties of the standard first-differenced GMM estimator. We consider two approaches to estimation. The first approach extends the model by adding the observed initial values as an extra regressor. This allows consistent estimates to be obtained by error-components GLS. This estimator is shown to be equivalent to the optimal GMM estimator for the normal homoskedastic error components model. The second approach considers a mild restriction on the initial condition process under which lagged differences in the dependent variable can be used to construct linear moment conditions in the levels equations. The complete set of moment conditions can then be exploited by a linear GMM estimator in a system of first-differenced and levels equations, rendering the non-linear moment conditions redundant for estimation. This estimator is strictly more efficient than non-linear GMM when the additional restriction is valid. Monte Carlo simulations are reported which demonstrate the dramatic improvement in performance of the proposed estimators compared to the usual first-differenced GMM estimator, especially for high values of the autoregressive parameter.

This paper empirically tests whether the host country's financial reform promotes the inflow of foreign direct investment (FDI). We test the hypothesis on the reform period Chinese provincial yearly panel data. The system generalized method of moments (GMM) estimation shows that the effect of financial reform on inward FDI to GDP ratios is not statistically significant after controlling for other variables and time and province effects. Consistent with the previous studies, market size and openness to international trade have significant effects on the FDI/GDP ratio in both Least squares dummy variables and system GMM estimations.

BackgroundTobacco use continues to kill millions of people globally, making it one of the major causes of preventable deaths. Notwithstanding, there has been a very marginal fall in the prevalence of tobacco smoking in Africa. Since taxes (hence prices) are part of the main measures suggested to decrease the demand for tobacco products, this study investigates how tobacco taxation and pricing influence the prevalence of smoking in 24 African countries.MethodsUsing panel data on 24 African countries sourced from the World Health Organization (WHO) and the World Bank databases for the period 2010 to 2016, this study employs the system Generalized Method of Moments (GMM) estimator to investigate the effects of tobacco taxation and pricing on the prevalence of smoking. The system GMM estimator is used due its ability to deal with potential endogeneity of tobacco taxation and pricing: the likelihood that the prevalence of smoking can influence tobacco taxation and pricing which may lead to biased estimates.ResultsTobacco taxation and pricing have negative significant effects on the prevalence of smoking among the selected countries after controlling for growth of Gross Domestic Product (GDP) per capita, urbanization, death rate and net inflows of Foreign Direct Investment (FDI). Specifically, a percentage increase in tobacco price is found to decrease the prevalence of smoking by between 0.11 to 0.14%, while a percentage increase in tobacco tax decreases the prevalence of smoking by between 0.25 to 0.36%, all at 1% level of significance.ConclusionSince tobacco taxation and pricing are found to have negative significant effects on the prevalence of smoking, the implication is that, their use can be intensified by African policy makers towards achieving the WHO Framework Convention on Tobacco Control (FCTC) recommended targets and hence decrease the prevalence of tobacco smoking in Africa. Doing so may therefore help in achieving the Sustainable Development Goal (SDG) 3.5 (prevention and treatment of substance abuse), thereby reducing the colossal number of smoking attributable deaths.

This paper presents a dynamic model of the Effective Tax Rate (ETR) in the tourism sector. A dynamic model where the lagged endogenous variable ETR has been included as a regressor to identify the dynamic structure of the variable due to the existence of temporal adjustments between the short and long run in ETR payments has been estimated. The empirical analysis based on a panel data set over the 2008-2013 period explores the determinants of the ETR variable by using a Generalised Method of Moments (GMM) estimator controlling for heterogeneity in the tourism sector. The Arellano-Bond system GMM estimator has been used to estimate the model. The study seeks to shed light on the determinants of tax burden in the tourism sector covering the lack of studies on this topic. The findings obtained suggest that the ETR borne is determined by size, financing structure and type of entity. We deem the finding of the existence of non-linear relationships between ETR and size and financing structure relevant.

This paper presents a robust M-estimation approach for first-order panel autoregressive models, addressing the challenges posed by high persistence levels of the autoregressive parameter and individual heterogeneity. Generalized method of moments estimators widely used in dynamic panel models exhibit substantial finite sample biases and are sensitive to weak instruments, particularly as the autoregressive parameter gets close to unity. Our proposed weighted M-estimator, which uses a power function for the scale parameter in Huber’s loss function, offers a robust alternative. By minimizing the variance of model parameters through an optimal tuning parameter, our method enhances the efficiency and robustness of parameter estimates. We demonstrate the superiority of the proposed approach through several Monte-Carlo simulations and an application to hydro-electric power output data, providing comprehensive comparisons with existing generalized method of moments estimators.

This paper considers the estimation methods for dynamic panel data (DPD) models with fixed effects, which suggested in econometric literature, such as least squares (LS) and generalized method of moments (GMM). These methods obtain biased estimators for DPD models. The LS estimator is inconsistent when the time dimension (T) is short regardless of the cross-sectional dimension (N). Although consistent estimates can be obtained by GMM procedures, the inconsistent LS estimator has a relatively low variance and hence can lead to an estimator with lower root mean square error after the bias is removed. Therefore, we discuss in this paper the different methods to correct the bias of LS and GMM estimations. The analytical expressions for the asymptotic biases of the LS and GMM estimators have been presented for large N and finite T. Finally; we display new estimators that presented by Youssef and Abonazel [40] as more efficient estimators than the conventional estimators.

In this article we examine small sample properties of a generalized method of moments (GMM) estimation using Monte Carlo simulations. We assume that the generated time series describe the stochastic variance rate of a stock index. we use a mean reverting square-root process to simulate the dynamics of this instantaneous variance rate. The time series obtained are used to estimate the parameters of the assumed variance rate process by applying GMM. Our results are described and compared to estimates from empirical data which consist of volatility as well as daily volume data of the German stock market. One of our main findings is that estimates of the mean reverting parameter that are not significantly different from zero do not necessarily imply a rejection of the hypothesis of a mean reverting behavior of the underlying stochastic process.

Power infrastructure and income inequality: Evidence from Brazilian state-level data using dynamic panel data models

An optimal capital structure is the fundamental premise of dynamic trade-off theory. However, firms deviate from the optimal level and display adjustment behaviour. This mechanism is referred to as the speed of adjustment towards the point of optimality and implies an examination of the convergence process towards the optimal level. One of the key issues in manufacturing companies is their leverage ratios (Mukherjee and Mahakud, 2012); hence, we aim to investigate the capital structure dynamics of manufacturing firms in India. Included in this investigation is a sample of 55 Indian manufacturing firms listed on the NSE200 from 2009 to 2016. Based on the dynamic panel data model with system generalised method of moments (GMM) estimation, our findings indicate an adjustment speed for the sample firms of around 25%, with a half-life of nearly 2.4 years.

Panel data are a very valuable resource for finding empirical solutions to political science puzzles. Yet numerous published studies in political science that use panel data to estimate models with dynamics have failed to take into account important estimation issues, which calls into question the inferences we can make from these analyses. The failure to account explicitly for unobserved individual effects in dynamic panel data induces bias and inconsistency in cross-sectional estimators. The purpose of this paper is to review dynamic panel data estimators that eliminate these problems. I first show how the problems with cross-sectional estimators arise in dynamic models for panel data. I then show how to correct for these problems using generalized method of moments estimators. Finally, I demonstrate the usefulness of these methods with replications of analyses in the debate over the dynamics of party identification.

Against the backdrop of the deep integration of the global digital economy and cross-border e-commerce, and addressing the lack of measure theory and quantitative analysis challenges for high-dimensional dynamic data in this field, this study constructs a measure theory system for cross-border e-commerce markets that combines mathematical rigor and economic interpretability based on Carathéodory’s extension theorem. Based on functional analysis and measure theory, the study defines the market fundamental set as the topological product space of a time index set and a multi-dimensional transaction state space. By constructing a combined structure of a left-open right-closed interval semiring and a power set semiring that satisfies the closure of Boolean algebra operations, an algebraic framework is established for the unified measurement of continuous and discrete variables. On the semiring structure, a σ-finite premeasure integrating Lebesgue measure and counting measure is defined. With the help of the countable covering mechanism generated by outer measure and the measure screening rules of Carathéodory’s measurability condition, the axiomatic extension from premeasure to complete measure on the σ-algebra is completed. Through the verification of Carathéodory’s condition for subsets of null sets and the transmission of outer measure monotonicity, the completeness of the measure space is strictly proved, and the core property that “subsets of null sets must be measurable” is established, providing a solid measure-theoretic foundation for mathematical modeling of cross-border e-commerce markets. At the empirical analysis level, the study uses micro-panel data on global cross-border e-commerce transactions from 2018 to 2024. Through the Kolmogorov-Smirnov test in non-parametric hypothesis testing, the distribution isomorphism between the theoretical measure and empirical data is verified. Based on the measure space theory, a Generalized Method of Moments (GMM) panel regression model is constructed. System GMM and Difference GMM estimation methods are used to handle endogeneity issues. Combined with instrumental variable methods and lag variable techniques, key parameters such as the logarithmic elasticity of economic scale between importing and exporting countries, the spatial decay effect of geographical distance, and the asymmetric inhibitory effect of tariff policies are quantitatively analyzed. A graph neural network model integrating measure theory is innovatively designed. By introducing a completeness regular term, the measure constraints on null sets and their subsets are achieved. Combined with the SHAP value interpretability analysis method, the marginal contribution of each characteristic variable in model decision-making is revealed. The study finds that the constructed measure space not only satisfies the axiomatic requirements of modern measure theory such as completeness and σ-finiteness, but also through the empirical tests of the GMM model and graph neural network, it is confirmed that it can effectively characterize the economic scale effect, spatial distance decay law, and policy sensitivity characteristics in cross-border e-commerce transactions, providing a methodological innovation paradigm based on measure theory for quantitative analysis in the field of international business in the digital economy era.