Arellano-Bond Estimator Research Articles

Dynamic panel data modelling using maximum likelihood: an alternative to Arellano-Bond

ABSTRACTThe Arellano-Bond estimator is widely used among applied researchers when estimating dynamic panels with fixed effects and predetermined regressors. This estimator might behave poorly in finite samples when the cross-section dimension of the data is small (i.e. small ), especially if the variables under analysis are persistent over time. This paper discusses a maximum likelihood estimator that is asymptotically equivalent to Arellano and Bond (1991) but presents better finite sample behaviour. The estimator is based on an alternative parametrization of the likelihood function introduced in Moral-Benito (2013). Moreover, it is easy to implement in Stata using the xtdpdml command as described in a companion paper published in the Stata Journal, which also discusses further advantages of the proposed estimator for practitioners.

Labour Taxation and its Impact on Economic Growth – Complex Analysis

AbstractThe aim of the article is to provide a complex analysis of labour taxation impact on economic growth in OECD countries. As main approximators of taxation, implicit tax rates and the World Tax Index are used. Methods and tests of dynamic panel regression with the Arellano-Bond estimator are used from the methodological point of view. From the results of complex analysis, it is evident that there exists a non-linear relationship between tax revenues (implicit tax rates, world tax index) and tax burden (tax rates). There also exists a negative relationship between labour taxation and economic growth and the impact of labour taxation is the most harmful for economic growth. Therefore, in an effort to stimulate economic growth, labour taxation expressed by personal income taxes and social security contributions should be reduced.

Some Effects of Intellectual Property Protection on National Economies: Theoretical and Econometric Study

This paper aims to theoretically derive and afterwards econometrically assess the impact of intellectual property protection (IPP) on national economies. The authors’ main hypothesis is that by creating a form of non-market protection, IPP limits free competition and has no positive effects on national economies and the world economy in general. The hypothesis is tested through estimation of relationship between charges for the use of intellectual property and 1) gross domestic product, 2) GDP growth, 3) unemployment, 4) exports of high-tech products, 5) FDI outflow, and 6) expenses on research and development in a panel dataset of 146 countries in years 2005–2014 based Arellano-Bond estimator for dynamic panel models. The data tells us that changes in these charges have not a significant impact on the studied indicators, which counts against claims of positive impact of IPP on economies and growth.

Inflation and the public investment: Growth relationship in Vietnam

Public capital spending positively contributes to economic growth and development in many countries worldwide. However, questions concerning the importance of inflation in the public investment–growth relationship are of great interest. This study examines the role of inflation in the public investment–growth relationship in Vietnam using the two-step GMM Arellano-Bond estimators for a balanced panel data of 52 provinces during the period of 2005–2014. More interesting are the empirical findings. First, inflation significantly increases the volume of public capital spending. Second, public investment and inflation enhance economic growth, but their interaction term impedes it. Third, private investment, government recurrent expenditure, and trade openness are the significant determinants of growth. These findings suggest some important policy implications related to public capital spending and inflation in developing countries, specifically the Vietnam government.

Testing the Lawyer-Induced Litigation Hypothesis in Europe

Notwithstanding the benefits of competition within the lawyer profession, economic theory supports the existence of a lawyer-induced litigation effect. Given concerns about the growing litigiousness in many European countries and the growing awareness that observed increases in lawyers might further induce litigation rates, policymakers require a thorough understanding of the relationship between the number of lawyers and litigation rates. Utilizing a European cross-country dataset, we contribute to the scant empirical literature on the lawyer-induced litigation hypothesis. To address endogeneity problems that arise when estimating the effect of the number of lawyers on litigation, we use two strategies. Following existing literature, we first estimate our model by means of the 2SLS procedure. Second, we exploit the instrumental variable approach based on the linear GMM estimator of Arellano and Bond (1991). To date, the Arellano-Bond estimator has not yet been used to address the endogeneity concerns between lawyers and litigation rates despite its advantages and popularity in other research areas. The estimations result in a positive and significant effect of lawyers that is robust across regressions. We discuss the policy implications of our findings.

Heterogeneity in House Price Dynamics

To what extent do house price dynamics differ across market segments? And what determines this heterogeneity? We address these questions by analysing a data set of individual houses and mortgages, based on a survey of about 2,000 Dutch households over the period 2003-2011. We estimate a dynamic panel data model of house price dynamics by means of the Arellano-Bond estimator. Three main empirical results emerge. First, we generally find that house price dynamics imply a convergence towards their long-run equilibrium value, as indicated by a negative serial correlation coefficient and a positive estimated mean reversion coefficient. Second, there is evidence that the housing market in the Netherlands is inefficient. Third, there is important heterogeneity across different market segments. We document that the speed of convergence of house price dynamics and the efficiency of housing markets depends on the geographical location and degree of urbanization, the type and year of construction of a house, the type of mortgage financing and households’ sentiment about the medium-term outlook for income.

The Relationship between Inequality and Growth: Evidence from New Data

SummaryThe relationship between inequality and growth has attracted a lot of attention in the previous literature. Estimation of this relationship may be biased by simultaneity, omitted variables and measurement error. The present paper contributes to the existing work by introducing the wealth Gini coefficient as a new inequality measure. The most reliable and recent data on income inequality are used for estimation. We employ the Arellano-Bond GMM estimation technique and we find that there seems to be a positive relationship between wealth inequality and real per capita GDP growth, but this relationship is not robust to different model specifications.

INFLUENCE OF FINANCIALIZATION OF INCOME INEQUALITY IN ASEAN: DATA PANEL ANALYSIS

This paper examines the impact of financialization on income inequality in ASEAN-5 countries for the period of 1990-2013 by employing panel data analysis. The data was collected from various secondary sources by undertaking fixed effect model and generalized method moment. The result shows that there is a significant relationship between all financialization indicators and income distribution. Generalized method moment analysis using Arellano-Bond estimator also shows that all financialization indicators have a significant relationship with income distribution. There is no different sign estimator both in fixed model effect and generalized method moment analysis. This paper revealed that financialization indicators such as stock market capitalization and return on assets contribute positively to worsen income inequlality. Incontrast, domestic private debt securities have a negative effect on gini coefficient in ASEAN-5 countries indicating that increasing domestic private debt securities will improve income distribution in the region.

The Effect of Credit Risk and Capital Adequacy on the Profitability of Rural Banks in the Philippines

AbstractThis paper examines the credit risk and capital adequacy of the 567 rural banks in the Philippines to investigate how both variables affect bank profitability. Using the Arellano-Bond estimator, we found out that credit risk has a negative and statistically significant relationship with profitability. However, empirical analysis showed that capital adequacy has no significant impact on the profitability of rural banks in the Philippines. It is therefore necessary for the rural banks to examine more deeply if capital infusion would result in higher profitability than increasing debts. The study also implies that it is imperative for the banks to understand which risk factors have greater impact on their financial performance and use better risk-adjusted performance measurement to support their strategies. Rural banks should establish credit risk management that defines the process from initiation to approval of loans, taking into consideration the sound credit risk management practices issued by regulatory bodies. Moreover, rural banks need to enhance internal control measures to ensure the strict implementation of internal processes on lending operations.

The Effect of Credit Risk and Capital Adequacy on the Profitability of Rural Banks in the Philippines

Abstract This paper examines the credit risk and capital adequacy of the 567 rural banks in the Philippines to investigate how both variables affect bank profitability. Using the Arellano-Bond estimator, we found out that credit risk has a negative and statistically significant relationship with profitability. However, empirical analysis showed that capital adequacy has no significant impact on the profitability of rural banks in the Philippines. It is therefore necessary for the rural banks to examine more deeply if capital infusion would result in higher profitability than increasing debts. The study also implies that it is imperative for the banks to understand which risk factors have greater impact on their financial performance and use better risk-adjusted performance measurement to support their strategies. Rural banks should establish credit risk management that defines the process from initiation to approval of loans, taking into consideration the sound credit risk management practices issued by regulatory bodies. Moreover, rural banks need to enhance internal control measures to ensure the strict implementation of internal processes on lending operations.

Heterogeneity in House Price Dynamics

To what extent do house price dynamics differ across market segments? And what determines this heterogeneity? We address these questions by analysing a data set of individual houses and mortgages, based on a survey of about 2,000 Dutch households over the period 2003-2011. We estimate a dynamic panel data model of house price dynamics by means of the Arellano-Bond estimator. Three main empirical results emerge. First, we generally find that house price dynamics imply a convergence towards their long-run equilibrium value, as indicated by a negative serial correlation coefficient and a positive estimated mean reversion coefficient. Second, there is evidence that the housing market in the Netherlands is inefficient. Third, there is important heterogeneity across different market segments. We document that the speed of convergence of house price dynamics and the efficiency of housing markets depends on the geographical location and degree of urbanization, the type and year of construction of a house, the type of mortgage financing and households' sentiment about the medium-term outlook for income.

Customer Perception Measures Driving Financial Performance - Theoretical and Empirical Work for a Large Decentralized Banking Group

There are many references in literature to customer satisfaction and related non-financial measures driving the financial performance of a company. Here we report results of analysis in the North-European financial sector, mainly banking. Based on proposed financial and customer perceived KPIs, operational measures are devised and measured for the studied corporation on different levels from global-corporate to individual branches. In addition, possible extensions to other industries of this relationship are studied and briefly reported. The analysis is based on panel approach where cross-section and time-series observations are studied for major actors. The Arellano-Bond estimation technique is used throughout.

Demographic Changes and Economic Growth: an Empirical Analysis

In this paper, we examine the overall effect of demographic transition on economic growth in the context of globalization. Theoretical foundations are based on the Solow–Swan model extended to include demographic variables. The GDP growth is modeled by using fixed effects unbalanced panel data and Arellano-Bond dynamic panel GMM estimators. In both regressions we use the KOF Index of Globalization in order to control for the influence of globalization in economic growth. The results based on data from 84 countries over the period 1970–2009 suggest that GDP per capita growth is negatively related to youth and old-age dependency ratios, and positively related to the growth differential between the working-age population and the total population. Moreover, forecasts suggest that the overall effect of the population dynamics will have a negative effect on economic growth in all developed countries over the period 2010-2100, while having a positive effect on almost developing economies.

Board gender diversity and firm performance: evidence from India

This study examines the impact of board gender diversity on financial performance of listed Indian firms in a dynamic modelling framework. Using a firm-year unit of analysis, a sample of 148 publicly listed firms across multiple industries have been studied over a period of five financial years namely FY 2008–2009 to FY 2012–2013. Employing panel data analysis, percentage of women directors is taken as the independent variable and firm performance measured by return on assets (ROA) and Tobin’s Q as the dependent variables. The primary results of the study using ordinary least squares (OLS) and fixed effects (FE) estimation models point towards a positive and significant relationship between percentage of independent women directors (IWD) and firm performance. However, results are reversed when the theoretically superior Arellano Bond estimation is used. Findings of the study indicate that the number of companies with no IWDs is reducing across the 5 years of study. This may be due to external pressure created by stakeholders. Also, the number of companies with one IWD is increasing over the period of the study, while the number of companies with two or three or more directors is more or less the same. The number of two or three IWD companies remaining the same could arguably be due to lack of availability of independent directors who are women.

The Effect of Serial Correlation in Estimating Dynamic Panel Data Models

There are several methods of estimating dynamic panel data models in the context of both micro-economic and macro-economic data.  This paper investigates the performance of five different estimators of dynamic panel data models (the random effect model) when the disturbance term is serially correlated.  A  Monte Carlo experiment was conducted when individual, N is large and time dimension, T is finite and the error component model is assumed to be serially correlated. The bias and Root Mean Square Error criterion were used to access the performance of different estimators under consideration. We found that the Anderson-Hsiao using lagged differences as instrument (AH(d)) performs better when the time dimension is small (T=5), Anderson-Hsiao using lagged levels as instrument (AH(l)) performs better when T is moderate(T=10) and the first step Arellano-Bond estimator (ABGMM1) outperforms all other estimators when T increases to 20. For a dynamic panel data with large time dimension, we suggest that the first step Arellano-Bond Estimator (ABGMM1) Estimator is appropriate.  The result shows that the bias of the first step Arellano-Bond estimator (ABGMM1) estimate is severe with small time dimension and the ordinary Least Square (OLS) and Least Square Dummy Variable (LSDV) are also bias when T is small.  It was discovered that the effect of serial correlation is negligible irrespective of the order.    

Revisiting The Relationship Between Financial And Environmental Performance: Does Granger Causality Matter?

This study rigorously investigates two ongoing issues about the relationship between environmental performance and financial performance: its sign (negative or positive) and direction of causation. The results from the longitudinal sample of US heavy-polluting industries between 1991 and 2005 support the positive relationship between EP and FP. We also test the Granger causal relationship by applying Arellano-Bond estimator. The results present that the causal direction is contingent on the selection of financial performance measures and on the characteristics of sub-groups classified by environmental performance. Namely, we find that the causality is valid only in high pollution-intensive industry group in terms of the one-year lagged accounting-based FP. A weak reverse direction was found only in the pollution-intensive industry group with Tobins q. The findings clearly suggest that it is necessary to use a consistent estimator when examining causality with longitudinal data in a dynamic setting.

Does regulatory discretion increase the unofficial economy? Evidence from panel data

One factor that contributes in the size of the shadow economy is the regulation of business activities. This paper provides empirical analysis of the effects of regulatory discretion on the unofficial economy. It adds to the previous findings by gathering evidence from a large data set of 162 countries for the 1999 to 2007 period. Going beyond simple correlation, it uses the Arellano-Bond estimator to investigate the dynamics and causal effects of regulation on the shadow economy. We find that increase in regulation increases the size of the shadow economy.

Effects of fiscal deficit and money M2 supply on inflation: Evidence from selected economies of Asia

A sustained high growth rate of gross domestic product at a low inflation is one of the main goals of the majority of macroeconomic policies, so keeping the price stability plays an important role in determining the growth rate of output. This paper empirically investigates effects of fiscal deficit and broad money M2 supply on inflation in Asian countries, namely Bangladesh, Cambodia, Indonesia, Malaysia, Pakistan, Philippines, Sri Lanka, Thailand, and Vietnam in the period of 1985-2012. By applying the Pooled Mean Group (PMG) estimation-based error correction model and the panel differenced GMM (General Method of Moment) Arellano-Bond estimator, the study finds out broad money M2 supply has significantly positive impact on inflation only in the method of PMG estimation whereas fiscal deficit, government expenditure and interest rate are the statistically significant determinants of inflation in both methods of estimation

Gibrat's Law and the Impact of Ownership: A Case Study of Croatia's Hotel Industry

This paper tests the hypothesis that in conditions of economic transition Gibrat's Law of proportionate growth holds, regardless of the type of firm ownership. The hypothesis is tested on a population of Croatian hotel companies, divided into three ownership type groups, operating continuously from 1998 to 2008. The developed dynamic multiple linear regression model of Croatian hotel firms evaluated by the two step Arellano–Bond estimator is used as a basis for analysis. Estimation of model parameters suggests that the dynamics of firms in transition conditions are not just a reflection of random effects, but are also affected by size and ownership factors. The results show that smaller companies grow more rapidly than larger ones and that growth varies depending on firm ownership, with slower growth in state-owned firms.

Credit risk and universal banking: evidence from the banking industry in Ghana

Using a dynamic panel data and an Arellano-Bond estimation technique, we estimate the determinants of credit risk and the effect of the introduction of universal banking licence on credit risk in the banking industry of Ghana. We find that the effect of universal banking policy on credit risk in the banking industry depends on the definition of credit risk. Using total loan to total asset ratio as a proxy for credit risk, we observe a positive effect of universal banking policy on credit risk in all our models, indicating that universal banking policy has the potential of increasing credit risk. However, there is a mixed and weak effect of universal banking policy on credit risk when we define credit risk as bad debt to total loan ratio. Also, we find that both bank-specific and macroeconomic variables do explain credit risk in the banking industry of Ghana.