Panel Data Model Research Articles

COVID-19 and Market Response: Evidence From Listed Firms in Tanzania and Kenya

This study investigates the effects of COVID-19 on the financial performance of listed firms in the financial and consumer goods industries in Tanzania and Kenya. The choice of Tanzania and Kenya as focal points is motivated by their contrasting responses to the pandemic and their roles as economic powerhouses in the region. Using data from the Dar es Salaam Stock Exchange and Nairobi Stock Exchange spanning the period from 2015 to 2022, the study employs the Dynamic panel-data model, the two-step system GMM, to quantify the impact of the pandemic. The research has two specific objectives: to analyze the effect of COVID-19 on the financial performance of listed firms in the financial industry and to assess its impact on the consumer goods industry in both countries. Key findings reveal that in the financial sector, firms showed resilience with a positive impact on profitability during the pandemic, driven by the adoption of digital financial services and effective risk management. In contrast, the consumer goods sector experienced a significant negative impact, highlighting severe disruptions in supply chains and consumer demand. Notably, firms in Tanzania outperformed those in Kenya, due to less restrictive COVID-19 measures. These findings suggest policymakers should support digital innovations, prudent leveraging, and economic growth to sustain and improve firm profitability during future disruptions.

Multiple Structural Breaks in Interactive Effects Panel Data Models

ABSTRACTThis paper develops new econometric methods for multiple structural break detection in panel data models with interactive fixed effects. The new methods include tests for the presence of structural breaks, estimators for the number of breaks and their location, and a method for constructing asymptotically valid break date confidence intervals. The new methodology is applied to a large panel of US banks for a period characterized by massive quantitative easing programs aimed at lessening the impact of the global financial crisis and the COVID‐19 pandemic. The question we ask is as follows: Have these programs been successful in spurring bank lending in the US economy? The short answer turns out to be: “No”.

The macroeconomic determinants of trade openness in Latin American countries: A panel data analysis

Background Trade openness shows a positive impact on economic growth, supported by economic theory, and export diversification and economic complexity show a positive dynamic in trade openness in the world; however, a specificity is generated in South American countries. Therefore, the objective of the research is to analyse the macroeconomic determinants of trade openness in Latin American countries. Methods The research approach was quantitative and explanatory using panel data methodology from the databases of the World Bank, Harvard University and the Economic Commission for Latin America and the Caribbean for the period 2000-2020. Results The fixed effects panel data model showed that the variables that had a negative impact on trade openness were GDP, the economic complexity index and the logistic performance index, while the variables that had a positive impact were exports of high-tech products (a proxy for innovation), exports, imports, research and development expenditure and interregional trade in goods. Conclusions Therefore, during the analysis period of 2000-2020 in South America, based on the panel data analysis under fixed effects, a total of 8 countries had a negative impact on trade openness, and only the economies of Chile, French Guiana, and Brazil had a positive impact on trade openness; these economies are characterized by their better performance in the economic complexity index, their higher percentage of budget for research and development expenses, and their trade policies oriented towards the industrialization of their value-added products.

Econometrics of Climate Change Research

The econometrics of climate change explores the intricate interplay between economic activity and climate dynamics, offering empirical insights into the causes, impacts, and mitigation of global climate change. This research applies advanced econometric techniques to quantify the economic consequences of environmental changes and evaluate the effectiveness of climate policies. By leveraging panel data models, time-series analysis, and causal inference methods, this study investigates critical topics such as the economic costs of extreme weather events, the efficacy of carbon pricing mechanisms, and the role of renewable energy adoption in mitigating climate risks. Additionally, this research incorporates machine learning techniques to enhance predictive accuracy in modeling future climate-economic interactions. Through rigorous empirical analysis, the study provides actionable recommendations for policymakers to design sustainable strategies that balance economic growth with climate resilience. The findings contribute to a deeper understanding of the socioeconomic dimensions of climate change, emphasizing the importance of evidence-based decision-making in addressing one of humanity’s most pressing challenges.

Correlation analysis of landscape patterns and urban thermal environment in Kunming based on a panel data model

With the development of urbanization, the spatial and temporal distribution characteristics of the urban landscape pattern play a decisive role in the intensity of the urban heat island (UHI) effect. A panel data model was constructed to study the relationship between the UHI effect and landscape pattern in Kunming from 1995 to 2020 at four different scales. The results indicate: (1) The landscape pattern of Kunming changed obviously with time, the artificial patch increased, the natural patch decreased, and the UHI effect became more and more obvious; (2) With an increase in scale, the number of influencing variables continues to grow, and the impact of artificial patches gradually intensifies; (3) The normalized difference water index (NDWI) has the greatest influence on the UHI, and the cooling effect is more obvious with the increase in scale. Unlike previous studies, the spatial configuration of the landscape in Kunming City had a stronger effect on the UHI effect than the landscape grouping and vegetation index; (4) This paper introduces the panel data model into the discussion of the UHI for the first time, providing a new method for better understanding the changing patterns of the urban thermal environment.

Drivers of Cooperation in Innovation by Energy Firms in Spain

AbstractInnovation by energy firms is critical for facing the energy transition and the challenge of climate change. Innovation is a complex process, and firms increasingly resort to cooperation with other companies and institutions in their innovation activities. In the energy sector, suppliers have always played a very important role in the technological advances of this industry. The objective of this paper is to analyse the determinants for engagement in cooperation in innovation by energy firms. In this analysis, we distinguish by the type of partnership, whether suppliers or research organisations (universities and research centres). We consider the factors proposed by the industrial organisation literature and the reasons given for firms to innovate, to explain decisions to cooperate. For the empirical analysis, we use a sample of energy firms from the Spanish Technological Innovation Panel (PITEC) for the period 2004–2016. To carry out the estimations we use binary models for panel data. In order to correct for endogeneity of the relevant variables, some of which are binary, we have relied on the panel data version of the special regressor method. Our results show the important role of incoming spillovers and innovation objectives related to reducing the environmental impact and meeting environmental regulatory requirements to explain cooperation in innovation by energy firms.

Modeling ICT adoption and electricity consumption in emerging digital economies: Insights from the West African Region

This study investigates the impact of Information and Communication Technologies (ICT) on electricity consumption in West Africa, employing a dynamic panel data model. The results show a significant long-term positive effect of ICT adoption on electricity consumption. Notably, internet connections increase the demand for electricity, with estimates ranging from 13.4 % to 19.3 %. While mobile phone subscriptions demonstrate modest positive effect of 6.85 %, personal computer ownership appears to have a negligible impact.The study contributes to the existing literature by offering a detailed examination of the distinct effects of different ICT components on electricity consumption, incorporating a novel estimation approach and sensitivity analyses that account for the COVID-19 pandemic and the Anglo-French linguistic divide. What's more, the analysis constitutes an initial effort in the examining both short-term and long-term dynamics of the ICT-electricity relationship in West African region.

Do sustainable business practices enhance firm profitability? An empirical study of Indian listed companies

This study employs a panel data model to examine the impact of sustainable business practices on profitability in the Indian market, focusing on 49 companies listed in the S&P BSE ESG 100 index from 2015 to 2022. Sustainable business practices are measured by ESG composite scores and individual environmental, social, and governance scores. Profitability is represented by return on equity and return on assets. Utilizing the Panel Corrected Standard Error technique to address data issues like autocorrelation and heteroscedasticity, the study finds that sustainable business practices insignificantly impact profitability. However, the social pillar has a significantly positive correlation with return on assets, with each unit improvement in the social score resulting in a 0.1323 increase in return. Conversely, the governance pillar negatively impacts return on assets, with each unit increase in governance score resulting in a decrease of 0.1527 units in profitability. Interestingly, larger companies experienced reduced returns on both assets and equity, as financial risk also lowered returns. These findings emphasize the relevance of companies’ socially responsible behavior, suggesting that managers and investors should prioritize sustainable practices for long-term benefits. Additionally, the findings advocate for robust regulatory frameworks focused on sustainability.

Horizontal inequity in the use of mental healthcare in Australia.

For people experiencing mental health problems, timely access to high-quality healthcare is imperative for improving outcomes. However, limited availability of services, high out-of-pocket costs, insufficient health literacy and stigmatizing attitudes may mean people do not receive the necessary treatment. We analyze Australian longitudinal data to document the extent and predictors of horizontal inequity in mental healthcare use among people with a newly developed mild or moderate mental disorder. Importantly, we compare people with similar health, residing in the same area, thus controlling for differences in healthcare needs and availability of services. Results suggest that mental healthcare use is not significantly associated with household income or financial hardship. In contrast, we find significant inequities by educational attainment, with university graduates around 50% more likely to receive mental healthcare than high-school dropouts. These findings are robust across subsamples and alternative modeling approaches, including panel data models with individual fixed-effects. Additional explorations of the education gradient suggest a potential pathway through mental health-specific knowledge and attitudes.

Contrasting performance of panel and time-series data models for subnational crop forecasting in Sub-Saharan Africa

We comprehensively examine methodologies tailored for subnational crop yield and production forecasting by integrating Earth Observation (EO) datasets and advanced machine learning approaches. We scrutinized diverse input data types, cross-validation methods, and training durations, focusing on maize production and yield predictions in Burkina Faso and Somalia. Central to our analysis is the comparative assessment of using time-invariant features within a panel data (PD) model versus a time-series data (TD) model. The TD model performed well in predicting both production and yield, while the PD model offered comparable yield predictions. Time-invariant features such as livelihood zones, soil properties, and cropland extents enriched the spatial understanding of crop data, enhancing the R-squared by 0.09 (0.21) for production and 0.11 (0.03) for yield, with corresponding reductions in the Mean Absolute Percentage Error by 90 % (238 %) for production and 5 % (4 %) for yield in Burkina Faso (Somalia). While Burkina Faso's consistent crop data allowed for effective modeling with brief training, Somalia benefited from the adaptability of the PD model to crop statistics outliers, particularly with extended training in high-producing regions. The PD approach showed promise in addressing data gaps, although predicting crop productions for unobserved districts remained a challenge. Our findings highlight the harmonious integration of EO data and machine learning in the field of agricultural forecasting and emphasize the importance of region-specific methodologies, especially in the rapidly changing landscape of EO data convergence.

The Refinement of a Common Correlated Effect Estimator in Panel Unit Root Testing: An Extensive Simulation Study

The Common Correlated Effect (CCE) estimator is widely used in panel data models to address cross-sectional dependence, particularly in nonstationary panels. However, existing estimators have limitations, especially in small-sample settings. This study refines the CCE estimator by introducing new proxy variables and testing them through a comprehensive set of simulations. The proposed method is simple yet effective, aiming to improve the handling of cross-sectional dependence. Simulation results show that the refined estimator eliminates cross-sectional dependence more effectively than the original CCE, with improved power properties under both weak- and strong-dependence scenarios. The refined estimator performs particularly well in small sample sizes. These findings offer a more robust framework for panel unit root testing, enhancing the reliability of CCE estimators and contributing to further developments in addressing cross-sectional dependence in panel data models.

Investigating the Nexus Between Energy Transition Reporting Practices and Corporate Efficiency in the European Agri-Food Sector

The research paper investigates the nexus between energy transition reporting practices and corporate efficiency of listed European companies from the agri-food sector. The study relies on key energy-related and financial indicators and logistic regression analysis conducted on 219 EU business entities publishing their financial and non-financial reports between 2004 and 2023. Based on the distribution of financial metrics in the sample, we assumed that entities reporting data on energy transition, either partially or fully, could achieve higher profitability and simultaneously have lower liquidity than non-reporting companies. The panel data model indicated a strong relationship between the reporting status of a business entity, its revenue, and the time variable, demonstrating that the likelihood of providing information on energy transition was associated with the size of a company and increased systemically over time. However, further regression analysis revealed a lack of a persistent, significant relationship between the key financial indicators and the entities’ energy transition reporting status. Considering the substantial changes in the EU regulatory environment associated with introducing CSRD, we conclude that with increasing legal pressure over time, companies will gradually shift towards standardized industry-related reporting practices, resulting in more consistent and transparent evidence of their energy transition strategies.

Incidence of unemployment and poverty on migration flows in the South-North international corridor (1990–2022). An econometric panel data approach

The aim of this research is to determine the incidence of socioeconomic variables in migration flows from the main countries of origin that form part of the international South-North migration corridor, such as Mexico, China, India, and the Philippines, during the 1990–2022 period. The independent variables considered are GDP per capita, unemployment, poverty, higher education, and public health, while the dependent variable is migration flows. An econometric panel data model is implemented. The tests conducted indicate that all variables have an integration order of I (1) and exhibit long-term equilibrium. The econometric models used, Dynamic Ordinary Least Squares (DOLS) and Fully Modified Ordinary Least Squares (FMOLS), reveal that unemployment and poverty had the strongest influence on migration flows. In both models, within this international migration corridor, GDP per capita, higher education, and health follow in order of importance.

Systemic risk spillovers among global energy firms: Does geopolitical risk matter?

In recent years, the worsening global geopolitical conditions have led investors and policy makers to become increasingly concerned about systemic risk in the global energy market. However, the existing literature has little empirical evidence on this problem from a geopolitical perspective. Based on an Elastic-Net-VAR model for depicting high-dimensional left-tail interdependence, this paper measures time-varying systemic risk spillovers among 212 energy firms in 36 countries. Then, a panel data model is established to examine the impact of geopolitical risk (GPR) on risk spillovers. Our results indicate that the GPR of a country directly intensifies the risk spillovers of the country's energy firms, as well as spreads to other countries based on geographic proximity and energy trade flows and indirectly intensifies the risk spillovers of the energy firms in these countries. Specifically, the indirect effects of GPR are more pronounced than the direct effects for fossil fuel firms, in oil-consuming countries, and during stable periods in global geopolitics. Moreover, the potential firm-level mechanisms through which GPR intensifies risk spillovers are declines in asset turnover, deceleration in corporate investment, and negative market forecasts. These findings can help to mitigate the adverse effects of GPR on energy firm performance, national energy security, and stability in the global energy market.

The interaction of income inequality and energy poverty on global carbon emissions: A dynamic panel data approach

Income inequality and energy poverty are critical obstacles to the worldwide low-carbon transformation and deeply affect human behavior. Applying a dynamic panel data model, this study investigates the effect of income inequality and energy poverty on global carbon emissions. We determine the effect of the interaction between income inequality and energy poverty on the global low-carbon transformation based on a panel data set of 193 countries from 1990 to 2019. A one standard deviation decrease in the Gini coefficient causes a 2.98 % decrease in carbon emissions per capita, with the median value of energy poverty. However, in poor countries where the proportion of population with access to electricity is less than 86.0 %, reducing income inequality will increase carbon emissions. The role of energy poverty on carbon emissions per capita is also affected by income inequality. When the Gini coefficient is lower than 0.461, increasing access to electricity will reduce carbon emissions. In contrast, when the Gini coefficient is higher than the critical value of 0.461, increased access to electricity will raise carbon emissions. These findings indicate a new strategy for advancing low-carbon transformation based on the interrelationship between income equality and energy poverty eradication.

The Role of Infrastructure Investment on Inclusive Growth and Human Development Index: Evidence from Emerging Economies

The paper examines the effect of infrastructure investment on the Human Development Index (HDI) score for five middle-income countries, namely Brazil, South Africa, Turkey, Mexico and Vietnam. The dynamic panel data model was used in the study. Data was sourced from the World Bank and the United Nations Development Programme focused on the prevalence and utilisation of five types of infrastructure in the countries mentioned above: electricity, water, sanitation, transport, telecommunications, and schools. The findings show that HDI is too narrow to be used as the main tool to measure human development and suggest that water and sanitation as well as the electrification of households were crucial infrastructures that had a positive impact on the HDI and be viewed as one type of infrastructure when researching the relationship between infrastructure investment and the HDI. The paper concluded and highlighted the need for infrastructure investors and policymakers to have a multi-dimensional approach to measuring the impact they would like to make. In this way, they would have more pronounced insights about which infrastructure they should invest in and how it will improve the wellbeing of society.

Indicators of Attracting Foreign Direct Investment in Developing Countries: Evidence from Vietnam

In today’s global economy, whether in advanced or emerging markets, the importance of being open to trade and investment is widely acknowledged as a key driver of economic growth. This economic openness is primarily demonstrated through the unrestricted exchange of goods and services as well as the free movement of international capital. While previous studies have investigated the effects of export-driven, import-driven, and capital-driven growth strategies, this research focuses on analyzing the impact of each indicator of the Provincial Competitiveness Index (PCI) on attracting foreign direct investment (FDI). By utilizing a panel data model covering 63 provinces and cities in Vietnam from 2018 to 2022, this study explores the correlation between PCI, FDI, and economic expansion. Findings suggest that export-oriented growth policies can be more effective in fostering the development of Asian emerging economies than FDI-centric approaches. Nonetheless, FDI continues to be crucial for technology transfer, capital accumulation, and knowledge exchange in management. Regions with advanced economies are more appealing to FDI, while provinces with distinctive industrial strengths also attract foreign investment. To further boost FDI inflows, it is advised that the government streamline market entry procedures, reduce administrative and tax burdens, increase transparency, and promote fair competition. These measures are anticipated to improve the investment climate and enhance competitiveness on the global stage.

Identification of Average Marginal Effects in Fixed Effects Dynamic Discrete Choice Models

Abstract In nonlinear panel data models, fixed-effects methods are often criticized because they cannot identify average marginal effects (AMEs) in short panels. In contrast with that criticism, we prove the point identification of different AMEs, including causal effects of changes in the lagged dependent variable or the last choice's duration, in a panel dynamic logit model for T as small as three. Our proofs are constructive and provide simple closed-form expressions for the AMEs in terms of probabilities of choice histories. We illustrate our results using Monte Carlo experiments and with an empirical application of a dynamic model of consumer brand choice.

Combining Instrumental Variable Estimators for a Panel Data Model with Factors

We address the estimation of factor-augmented panel data models using observed measurements to proxy for unobserved factors or loadings and explore the use of internal instruments to address the resulting endogeneity. The main challenge consists in that economic theory rarely provides insights into which measurements to choose as proxies when several are available. To overcome this problem, we propose a new class of estimators that are linear combinations of instrumental variable estimators and establish large sample results. We also show that an optimal weighting scheme exists, leading to efficiency gains relative to an instrumental variable estimator. Simulations show that the proposed approach performs better than existing methods. We illustrate the new method using data on test scores across US school districts.

The Governance-Growth Nexus and Its Environmental Implications in South Asia

This research delves into the correlation between economic growth, governance quality, and CO2 emissions within a cohort of seven nations in South Asia: Between 1996 and 2020, Bangladesh, Bhutan, India, Iran, Nepal, Pakistan and Sri Lanka. Using dynamic panel data models and fixed effects, this research documents the role of per capita gross domestic product (GDP) and the capacity of governance to affect carbon dioxide (CO2) emissions. It finds a direct correlation to CO2 emissions and economic growth and hence associate increase GDP per capita to increase in environmental degradation. Yet, enhanced governance is shown to significantly lower CO2 emissions in countries like Bangladesh, India, Nepal and Pakistan, and contributes to increasing CO2 emissions in others. In addition, economic growth and governance quality interaction led to the finding that good governance can moderate the negative environmental effects of economic growth. The uncovering of these findings underscores the importance of governance in meeting environmental sustainability and economic growth objectives in South Asia. The findings provide important policy guidance on improving governance structures to deal more efficiently with the environmental problems facing the region.