Robust Least-squares Research Articles

The Nexus of Crowdfunding and e-Wakaf to Islamic Fintech in Indonesia in the Era of Industrial Revolution 5.0

This study analyses the contribution of digitalisation in Islamic finance through the application of Islamic crowdfunding and e-wakaf instruments in supporting the development of Islamic fintech in Indonesia, especially in the era of the Industrial Revolution 5.0. Digitalisation in the Islamic finance sector plays a strategic role in expanding access to financial inclusion and facilitating more effective community involvement in sharia-based economic activities. Using the Robust Least Squares (RLS) method, this study utilises secondary data for the period 2018 to 2023 to evaluate the impact of Islamic crowdfunding and e-wakaf on the growth of Islamic fintech. The results show that Islamic crowdfunding significantly expands access to alternative funding, especially for small and medium enterprises (SMEs), while e-wakaf improves transparency and efficiency of waqf asset management through digital technology. These two instruments simultaneously contribute positively to the strengthening of the Islamic fintech ecosystem in Indonesia, creating a strong foundation for broader and sustainable financial inclusion. The findings provide important perspectives for the development of innovative policies and strategies in advancing the Islamic financial sector in the digital era.

Oman’s Green Horizon: Steering Towards Sustainability Through Decarbonization and Energy Transition

This paper examines the determinants of CO2 emissions in Oman from 1990 to 2024, focusing on the impacts of energy consumption, economic growth, urbanization, financial development, and foreign direct investment. The analysis utilizes stepwise regression to systematically identify the most significant predictors, ensuring a parsimonious model. Robust least squares (ROLSs) are employed to account for potential outliers and heteroscedasticity in the data, providing more reliable estimates. Fully Modified Least Squares (FMOLSs) is applied to address issues of endogeneity and serial correlation, offering robust long-term coefficient estimates. Canonical cointegrating regression (CCR) further refines these estimates by handling non-stationary variables and ensuring consistency in the presence of cointegration. Cointegration tests, including the Johansen and Engle–Granger methods, confirm long-term equilibrium relationships among the variables; this study reveals several key findings. Energy use per capita (ENGY) and real GDP per capita (RGDPC) are consistently significant positive predictors of CO2 emissions. Urbanization (URB) also significantly contributes to higher emissions. Conversely, the Financial Development Index (FDX) and foreign direct investment (FDI) do not show significant effects on CO2 levels. The high R-squared values across models indicate that these variables explain a substantial portion of the variation in emissions. Cointegration tests confirm long-term equilibrium relationships among the variables, with the Johansen test identifying two cointegrating equations and the Engle–Granger test showing significant tau-statistics for FDX, ENGY, and URB. The VEC model further highlights the short-term dynamics and adjustment mechanisms. These findings underscore the importance of energy policy, economic development, and urban planning in Oman’s efforts towards sustainable development and decarbonization.

Renewable energy and CO2 emissions in developing and developed nations: a panel estimate approach

Emerging economies and ecosystems are critically dependent on fossil fuels, and a country’s energy dependence is a significant measure of its reliance on foreign suppliers. This study evaluates the impact of energy reliance on energy intensity, CO2 emission intensity, and the utilization of renewable resources in 35 developing and 20 developed nations, as well as the connection between renewable energy (REN), GDP growth, and CO2 emissions. This study employs the generalized linear model (GLM) and the robust least squares (RLS) method to assess the inverse association between renewable energy and developed and developing economy policymakers, utilizing unique linear panel estimate approaches (1970–2022). The impact of renewable energy as a response variable on economic growth, energy consumption, and CO2 emissions across four continents is investigated in this study. The findings indicate that developing countries experience a rise in per capita CO2 emissions if their renewable energy use exceeds their capacity. This finding remains significant even when other proxies for renewable energy use are introduced using modified approaches. Furthermore, it is particularly relevant to industrialized nations that possess more developed institutions. Even more surprisingly, in terms of the energy and emission intensity required for growth, energy dependence has accelerated all components. The regional analysis revealed a spillover impact in most areas, suggesting that the consequences of energy dependence are essentially the same in neighboring countries. The growth of the renewable energy sector and the decrease in greenhouse gas emissions depend critically on the ability of regional energy exchange unions to mitigate the negative environmental and economic impacts of energy dependency. These underdeveloped countries need to spend more on research and development to catch up technologically.

The economic determinants of world disorder events: An empirical analysis

This paper delves into the economic determinants of World Disorder Events (WDE) using robust empirical methodologies applied to a cross-section of world data over the period 1997-2022. By employing econometric models such as Robust Least Squares (RLS), complemented with Artificial Intelligence methods, such as Ridge Regression (RR) and Artificial Neural Networks (ANN), we uncover the influence of various economic, environmental, and health factors on the frequency and intensity of WDE. RR is used to address multicollinearity among predictors, thereby enhancing the reliability of our regression estimates. The robustness of our findings is further ensured through ANN models, which improve prediction accuracy and model stability. This analysis not only identifies key economic drivers of WDE but also offers policy recommendations to reduce the incidence and impact of these events. By integrating multiple applied techniques, this paper contributes to a more nuanced understanding of the complex interplay between economic conditions and global stability, offering valuable insights for policymakers and economic analysts.

Renewable Adoption, Energy Reliance, and CO2 Emissions: A Comparison of Developed and Developing Economies

Emerging economies and ecosystems rely heavily on fossil fuels, and a country’s energy dependence is a strong indicator of its reliance on foreign suppliers. This study investigates the impact of energy dependence on energy intensity, CO2 emission intensity, and the exploitation of renewable resources in 35 developing and 20 developed nations. It also explores the correlation between renewable energy, GDP growth, and CO2 emissions. This study utilizes the Generalized Linear Model (GLM) and the Robust Least Squares (RLS) method to investigate the negative correlation between renewable energy and policymakers in established and emerging economies. It also employs distinctive linear panel estimation techniques spanning from 1970 to 2022. This study examines the impact of renewable energy on economic growth, energy consumption, and CO2 emissions across four continents. Developing countries see an increase in per capita CO2 emissions when their utilization of renewable energy exceeds their capacity. Even with the introduction of several proxies for renewable energy use using changed techniques, this discovery remains valid. Moreover, this is particularly crucial for industrialized nations with well-established institutions. Energy dependency has increased the energy and carbon intensity needed for expansion across all components, which is surprising. The regional study discovered a spillover impact in most regions, indicating that the consequences of energy reliance are similar in neighboring countries. Regional energy exchange unions play a vital role in reducing the adverse environmental and economic impacts of energy dependence, which is essential for the growth of the renewable energy sector and the decrease in greenhouse gas emissions. Undeveloped countries need to enhance their investment in research and development to advance technologically.

The impact of aquaculture economics expansion on marine water quality in the EU Region

Water scarcity is a growing condition caused by climate change and human activity, and it influences and interacts with other stressors in freshwater and marine ecosystems, such as chemical pollution. Aquaculture production has a significant impact on the EU27 region's water stress and water contamination discharge levels. Therefore, the primary goal of this research is to examine how the aquaculture industry affects water contamination discharge in European Union developed countries (EU14) and European Union developing countries (EU13) from 1990 to 2023. Since the dependent variable's error terms are correlated with the independent variables, the endogeneity problem was solved with the use of robust least squares (RLS), two-stage least squares (2SLS), and ordinary least squares (OLS) estimators, which produced the major findings. According to the precise effect sizes, the aquaculture industry and gross domestic product are more important in determining water contamination discharge in developed EU14 countries than in developing EU13 countries. The precise magnitudes of the effect demonstrate that, compared to EU14 developed countries, water contamination discharge in EU13 developing countries is mostly determined by the use of hydrocarbons. However, as the precise magnitudes of the three estimators demonstrate, governance is more important in EU14 developed countries than in EU13 developing countries when it comes to controlling water contamination discharge. The authors advise policymakers to give policies targeted at improving the aquaculture industry's efficiency and green development top priority, especially in EU13 developing countries with unplanned aquaculture expansion and inefficient aquaculture industry outgrowth. The authors advise policymakers in the EU14 developed countries to take actions targeted at improving governance efficiency top priority.

Effect of Carbon Footprint on Agricultural Productivity in Nigeria: An Empirical Analysis

This study examines the relationship between carbon footprint (CFP) components and agricultural productivity in Nigeria, a critical area of investigation given the country's reliance on agriculture for economic stability, food security, and employment. Using time series data from 1990 to 2020, sourced from the Central Bank of Nigeria (CBN) and the World Bank, this study analyzes the effect of carbon dioxide (CO2), methane (CH4), and nitrous oxide (N2O) emissions on agricultural output. Employing Robust Least Square (RLS) regression and the Error Correction Model (ECM), the study finds that CO2 and CH4 emissions negatively affect agricultural productivity, with 1% increases in CO2 and CH4 emissions leading to approximate decreases in agricultural output by 2% and 3%, respectively. Conversely, a 1% increase in N2O emissions correlates with an 8% increase in agricultural output, attributed to the use of nitrogenbased fertilizers. The results confirm the presence of long-run equilibrium relationships among the variables, with approximately 32% of the previous year's disequilibrium corrected annually. The study's findings align with the Environmental Kuznets Curve (EKC) hypothesis, suggesting that Nigeria is in the early stages of economic growth where environmental degradation is pronounced. These insights underscore the need for sustainable agricultural practices and effective carbon emission mitigation strategies to enhance food security and support economic growth in Nigeria.

Unlocking SME investment potential: The determinants of an effective credit guarantee scheme in Morocco

This research seeks to identify the factors influencing the investment potential of SMEs following their receipt of government-guaranteed loans. To this end, an empirical methodology based on the statistical analysis of data collected from a representative sample of Moroccan companies was employed. This sample of 335 SMEs that had benefited from loans with government guarantees was selected at random to ensure its relevance to the population of SMEs in Morocco. The methodological approach is based on a regression analysis using the robust least squares (RLS) method. Firm profitability is positively related to higher investment, suggesting that government guarantees should encourage investment by profitable SMEs. Liquidity, repayment capacity and indebtedness at the time of applying for finance do not appear to influence investment. These elements can be improved after financing, which indicates that government guarantees should not penalize SMEs in difficulty. Decision-making maturity has a negative effect on investment, suggesting that young companies and entrepreneurs tend to invest more. A negative correlation is observed between company size and investment, which suggests that government guarantees should be geared towards small SMEs and young companies and entrepreneurs. Finally, managers with a large share of capital invest more, leading us to believe that government guarantees should favor this type of SME.

Economic Complexity, Institutions, and Property Rights

Objectives/Background: Property rights play a fundamental role in economics through rights to asset and resource owners, thereby enhancing their economic efficiency. The study investigates the relationship between property rights and economic complexity across countries classified by income levels, including high, middle, and low-income nations. Methods: The study utilized Robust Least Square (RLS) to obtain results from a secondary data set. Results: Our analysis reveals a positive relation between economic complexity and property rights across all income groups. It is suggested to have potential developmental paths for countries based on their income status such as those of low income and middle income groups. More specifically, it is proposes that low-income countries could benefit from the institutional improvements observed in high middle-income countries group. Whereas, high middle-income countries may find help in modeling their institutions after those of high-income countries. The approaches may help sustain and enhance institutions and foster an environment conducive to economic complexity. Conclusion: This research contributes valuable insights into the interplay between economic complexity and property rights across diverse income contexts, offering potential strategies for policymakers to enhance property rights and drive inclusive economic development.

The Roles of Export of Coffee Commodity and Macroeconomics Factors on Unemployment in Indonesia

Coffee as the second largest agricultural commodity export has contributed to the economies of various countries, including Indonesia. In addition to looking at the role of coffee commodity exports, an analysis of macroeconomic factors' impact on Indonesia's unemployment rate is also analyzed. Because it is known that the unemployment rate is not only caused by one sector but some things influence it, including macroeconomic factors. This study analyzes the role of coffee commodity exports and macroeconomic factors, including GDP, inflation, and interest rates, on Indonesia's unemployment rate. The data used in this study is interpolated secondary data for the period 2000 to 2021. The estimation method used in this study is Robust Least Square (ROBUSTLS) which will then be estimated again using the Autoregressive Distributed Lag (ARDL) method as a robustness test. The estimation results using the ROBUSTLS method prove that coffee commodity exports and macroeconomic factors significantly affect Indonesia's unemployment rate in aggregate. This form of influence is negative for coffee commodity exports (ExpCof), gross domestic product (GDP), and interest rate (IR). While inflation (Inf) has a positive impact on the unemployment rate (Ump). These findings are reinforced by the estimation results using the ARDL method with the result that ExpCof, GDP, and Inf have a significant relationship to Ump, while Inf is not as significant as the findings from the estimation results using the ROBUSTLS method.

Beyond climate change: Examining the role of environmental justice, agricultural mechanization, and social expenditures in alleviating rural poverty

Extreme weather events and extreme poverty are two sides of the same coin, with far-reaching consequences for emerging nations like Pakistan. Rural people are more likely to experience poverty and inequality as climate change worsens. This research aspires to close the gap between environmental ethics and justice by investigating how climate change issues contribute to poverty in Pakistan. The study used Robust Least Squares (RLS) regression to analyze the impact of water scarcity, extreme temperatures, and excessive rainfall on rural poverty in Pakistan from 1990Q1 to 2022Q4. Further, the study examines the effect of environmental justice interventions, access to healthcare and education, agricultural value-added and agricultural mechanization on the country's rural poverty. Results reveal that climate change contributes to rural poverty in Pakistan, while environmental justice initiatives, healthcare access, and agricultural automation alleviate poverty incidence. The Impulse Response Function (IRF) estimates suggested that rural poverty will be exacerbated over the next decade by water scarcity, high temperatures, and low agricultural value added but alleviated by excessive rainfall, environmental justice intervention, healthcare access, and agricultural mechanization. According to Variance Decomposition Analysis (VDA) projections, agricultural value added will substantially impact rural poverty by 2032, increasing it by 11.431%. Addressing these problems requires policymakers to prioritize the interests of the most marginalized groups by fostering fair results. Policies should cut GHG emissions and encourage sustainable development to combat climate change. Modernizing farming techniques and expanding access to healthcare are also necessary for increasing efficiency and production. It is essential to execute environmental justice interventions so that all communities have access to environmental resources and protections equitably. Promoting equitable outcomes and reducing poverty in Pakistan's climate change context may be achieved by closing the gap between environmental ethics and justice.

Vertical deformation analysis based on combined adjustment for GNSS and leveling data

A method is proposed to fuse the velocity data of the global navigation satellite system (GNSS) and leveling height via combined adjustment with constraints. First, stable GNSS–leveling points are uniformly selected, and the constraints of the geodetic height change velocity and normal height change velocity are given. Then, the GNSS vertical velocities and leveling height difference are used as observations of combined adjustment, and robust least-squares estimation are used to estimate the velocities of the unknown points. Finally, a vertical movement model is established with the GNSS vertical velocities and leveling vertical velocities obtained via combined adjustment. Data from the second-order leveling network and GNSS control points in Shandong Province are taken as test data, and eight calculation schemes are used for discussion. One of the schemes, the bifactor robust combined adjustment method based on variance component estimation with two kinds of vertical velocity constraints achieves the optimal results. The method applied in the scheme can be recommended for data fusion of GNSS and leveling, further improving the reliability of vertical crustal movement in Shandong Province.

Soft-sensing modeling of mother liquor concentration in the evaporation process based on reduced robust least-squares support-vector machine.

The evaporation process is vital in alumina production, with mother liquor concentration serving as a critical control parameter. To address the challenge of online detection, we propose the introduction of a soft measurement strategy. First, due to the significant fluctuations in the production process variables and inter-variable coupling, comprehensive grey correlation analysis and kernel principal component analysis are employed to reduce the input dimension and computational complexity of the data, enhancing the efficiency of the soft sensing model. The reduced robust least-squares support-vector machine (LSSVM), with its commendable predictive performance, is used for modeling and predicting the principal components. Concurrently, an improved Pattern Search-Differential Evolution (PS-DE) algorithm is proposed for optimizing the pivotal parameters of the LSSVM network. Lastly, on-site industrial data validation indicates that the new model offers superior tracking capabilities and heightened accuracy. It is deemed aptly suitable for the online detection of mother liquor concentration.

Evaluating the Economic and Environmental Repercussions of the Price Paradox in Natural Resource Commodities: Market Drivers and Potential Challenges for Sustainable Development

The natural resource commodity price paradox is a phenomenon that has been observed in the past. The price of a commodity constantly and unpredictably fluctuates. This phenomenon makes it difficult for businesses to plan for future needs and investments. This study examined the relationship between natural resource commodity prices, renewable energy demand, economic growth, high-technology exports, inbound FDI, and greenhouse gas (GHG) emissions in Pakistan, using the 1975 to 2020 time period. The robust least squares (RLS) regression results showed that natural resource commodity prices and economic growth increased GHG emissions. In contrast, there was a negative relationship between renewable energy demand (and high-tech exports) and GHG emissions in Pakistan. The results verified the resource price curse hypothesis and growth-associated emissions in a country. The Granger causality estimates showed the unidirectional relationship of renewable energy consumption with GHG emissions, natural resource pricing, and inbound FDI. Further, high-technology exports Granger caused GHG emissions and GDP per capita. The results verified the country’s growth-led green energy sources and inbound FDI, resource pricing-led inbound FDI, and GHG emissions-led resource pricing. The impulse response function suggested that resource commodity pricing and the country’s economic growth will likely increase GHG emissions in the next ten years. At the same time, green energy demand, technological advancements, and sustainable investment in cleaner production would help decrease GHG emissions over time. The variance decomposition analysis suggested that technology advancements would likely have greater variance shock on GHG emissions, followed by commodity resource pricing and green energy demand. The resource price paradox hampers economic and environmental outcomes, which need to be resolved through advancement in cleaner production technologies, adoption of green energy demand, and stabilization of resource commodity pricing that helps to move forward toward the sustainable development of the country.

The Economic Value of Natural Resources and Its Implications for Pakistan’s Economic Growth

Natural resources and ecological services provide the foundation for manufactured capital, increasing public financing and decreasing inequality by diversifying the economy. The exploitation of natural resources is frequently the backbone of economic stability in developing and middle-income nations. As a result of their importance, natural resources need vigilant and long-term management. Recent research has tested two hypotheses, the natural resource blessing hypothesis and the natural resource curse hypothesis, on the impact of a country’s natural resources on its economy. This research is an essential contribution to the growing body of work that attempts to quantify natural resource endowments’ role in national economic growth. Investigations focus on Pakistan and span the years 1975 through 2020. Robust Least Square (RLS) estimations show that coal rents, energy use, inbound FDI, and oil rents contribute to a country’s economic growth. While consumption of renewable energy sources and industrial value-added have a detrimental effect. Natural resources, foreign direct investment, energy consumption, and industrial ecology are predicted to significantly impact economic growth during the next decade, according to the Impulse Response Function (IRF) and the Variance Decomposition Analysis (VDA). The findings may provide helpful information for academic and governmental institutions to develop natural resource management policies for sustainable development.

An analysis of the success of fiscal adjustment in reducing public debt: Evidence from Pakistan.

This study seeks answers to questions such as: what is fiscal adjustment? Which fiscal strategy will result in a reduction in public debt liabilities? In the pursuit of answers to these questions, the study has defined two objectives. Firstly, the fiscal adjustment episodes must be identified in order to detach the discretionary fiscal stance; secondly, the success of these adjustment episodes in reducing public debt liabilities must be assessed. As a result, attempts will be made to undertake analyses that would simplify the issues underlying Pakistan’s practical policy options. A total of eleven adjustment episodes have been observed in a sample, ranging from 1976 to 2017, following Alesina and Ardagna’s definition. The descriptive analysis reveals that five episodes succeeded in reducing the public debt, while six episodes failed to reduce the ratio. Out of the five successful episodes, four are found to be spending-based and one is tax-based. To quantify the success of fiscal adjustment, the empirical model has been calibrated on Leibrecht and Scharler’s model and estimation is done via both the Ordinary Least Squares (OLS) and Robust Least Squares (RLS) methods. The RLS method produces better outcomes than the OLS method. Under RLS, all variables are significant except GDP growth, whereas in the OLS model, the election year and regime shift, together with GDP growth, are statistically insignificant. The fiscal adjustment’s composition reveals that spending-based consolidation boosts the chances of the fiscal adjustment’s success. Fiscal authorities should, therefore, adopt spending-based austerity measures to ensure the sustainability of public finances and prevent the negative macroeconomic consequences of unsustainable public debt.

Mitigating Carbon Emissions in China: The Role of Clean Energy, Technological Innovation, and Political-Institutional Quality

The global warming phenomena arise from the subject of climate change, which draws intellectuals’ attention toward replacing polluting energy sources with clean energy sources by continued deployment of innovations. Also, global warming problems put large pressure on governments, individuals, and policymakers. Therefore, for reliable energy supply and economic development, the target of achieving a low-carbon and sustainable environment is needed. In this light, we explore the role of clean energy and technological innovation in carbon emission reduction in China from 1995 to 2018. The key outcomes from the fully modified least-squares and robust least-squares indicate an elasticity of −0.065 and −0.075, respectively, for the nexus of renewable energy and CO2 emissions. Similarly, nuclear energy, technology innovation, and political-institutional quality have a negative influence on CO2 emissions. Furthermore, the granger causality demonstrates feedback between renewable energy and CO2 emissions, as well as between technological innovation and CO2 emissions. To achieve a cleaner environment, the implementation of the existing policy pathways is potentially geared toward applying technological innovations to produce renewable energy at lower costs.

The Impact of the Regional Trade Agreements on Inflow of Mexican Foreign Direct Investment: An Empirical Approach

This article aims to empirically evaluate, based on the annual time series from 1970 to 2018, the hypothesis that regional trade agreements (RTA) had a positive impact on the Mexican Foreign Direct Investment (FDI) inflow in this period. We use the North American Free Trade Agreement (NAFTA) to evaluate its impact in Mexico, which entered into force in 1994. In this context, our interest variable is the dummy d_1994, where from 1994 to 2018 it is equal to 1. We tested several empirical approaches based on ARDL models, robust least-squares methods as well as GMM methods. We also use Granger causality tests and impulse response tests based on the VAR system. All empirical models show that the estimated coefficient from the dummy variable, d_1994, is statistically significant and presents a positive sign. Moreover, the causality tests show that the variable d_1994 granger causes FDI as a proportion of GDP, and the impulse response tests validate the tested hypothesis as well.

AEROS: AdaptivE RObust Least-Squares for Graph-Based SLAM.

In robot localisation and mapping, outliers are unavoidable when loop-closure measurements are taken into account. A single false-positive loop-closure can have a very negative impact on SLAM problems causing an inferior trajectory to be produced or even for the optimisation to fail entirely. To address this issue, popular existing approaches define a hard switch for each loop-closure constraint. This paper presents AEROS, a novel approach to adaptively solve a robust least-squares minimisation problem by adding just a single extra latent parameter. It can be used in the back-end component of the SLAM system to enable generalised robust cost minimisation by simultaneously estimating the continuous latent parameter along with the set of sensor poses in a single joint optimisation. This leads to a very closely curve fitting on the distribution of the residuals, thereby reducing the effect of outliers. Additionally, we formulate the robust optimisation problem using standard Gaussian factors so that it can be solved by direct application of popular incremental estimation approaches such as iSAM. Experimental results on publicly available synthetic datasets and real LiDAR-SLAM datasets collected from the 2D and 3D LiDAR systems show the competitiveness of our approach with the state-of-the-art techniques and its superiority on real world scenarios.

Discretionary choices of commercial banks in Bangladesh: an earnings management approach

ABSTRACT Purpose- The study aims to trace out the factors contributing to earnings management practices in the commercial banks of Bangladesh. Methodology- The study used secondary data sources from the published audited annual reports of 32(Thirty-Two) commercial banks of Bangladesh from the year 2005-2018 of 425 observations. The study conducted preliminary diagnoses like normality, unit root, and Granger causality test to identify the data's nature and response. Moreover, the study performed the heteroscedasticity test, autocorrelation test, and fixed and random effect of the model to confirm the output's accuracy. Based on the above statistical diagnosis, the study has selected Robust Least Square (RLS) regression model to show the practice of discretionary choices in the banking sector of Bangladesh. Following Kanagaretnam et al.’s (2003), this study also derived discretionary and non-discretionary accruals from loan loss provisions. Findings- This study considered several factors like bank size (SIZEit), loan to deposit ratio (L/DEPit), non-performing loan to previous year’s total loan ratio (NPLRit-1), changes in non-performing loan to current total loan ratio (∆NPL/TLit), and changes in total asset to total loan ratio (∆TA/TLit) to show the effects on banks’ earnings management. It is found that SIZEit, NPLRit-1, ∆NPL/TLit and ∆TA/TLit have a positive and significant (p<0.01; p<0.05) effect on Bank‘s discretionary choice. However, L/DEPit positively affects earnings management but is statistically insignificant. Conclusion- Despite being a legal tool, earnings management is often involved with the controversy of being an unethical practice. However, there has been a lot of research on tracing earnings management in corporate firms based on discretionary and non-discretionary accruals. The study contributes to the existing literature and tries to explain the role of discretionary accruals in banks performance mostly in the submerged economy. Along with identifying significant variables, the study has tried to explain the implication of these findings suggesting some crucial steps that may help reduce the practice of earnings management as earnings management distorts the banks' financial position or any firm and misleads the investors. Keywords: Earnings management, discretionary accruals, panel data, commercial banks, Bangladesh. JEL Codes: C22, C23, G21