Research Articles (Business Management)

Permanent URI for this collectionhttp://hdl.handle.net/2263/2508

Browse

Now showing 1 - 20 of 419

Another generalised transmuted Rayleigh distribution theory, properties, and inference
Ashiagbor, Albert Ayi; Das, Sonali; Essel-Mensah, Kojo; Lawluvi, Emmanuel (Chinese Society for Science of Science and S&T Policy Research, 2025)
This paper introduces the Another Generalised Transmuted Rayleigh (AGTR) distribution, obtained by embedding the classical Rayleigh law within the Another Generalised Transmuted (AGT) family. The new model inherits the physical interpretability of the Rayleigh distribution while gaining two additional shape parameters that govern skewness and tail weight, enabling it to capture highly skewed and leptokurtic phenomena. We derive closed-form expressions for the probability density, cumulative, survival, hazard, and reverse-hazard functions and establish legitimacy conditions. Further analytical results include quantile and moment functions, R´enyi and Shannon entropies, incomplete moments, Lorenz and Bonferroni inequality curves, and several stochastic orderings. Parameter estimation is addressed via maximum likelihood; the observed-information matrix is provided for inference. A extensive Monte Carlo study, across sample sizes n = 25–1000, demonstrates that the maximum-likelihood estimators are consistent, nearly unbiased, and achieve nominal 95 % coverage with declining RMSE as n increases. Graphical illustrations confirm the AGTR distribution’s ability to reproduce monotone, bathtub, and non-monotone hazard shapes, underscoring its applicability to reliability analysis, survival studies, and risk modelling. The AGTR distribution thus offers a flexible, analytically tractable alternative to existing Rayleighbased extensions and enriches the toolkit for modelling skewed, heavy-tailed data.
A flexible kernel regression decomposition-based hybrid framework for forecasting foreign exchange rates: uncovering symmetric and asymmetric market dynamics
Iftikhar, Hasnain; Shah, Said Farooq; Almuhayfith, Fatimah E.; Rodrigues, Paulo Canas (MDPI, 2026-08-14)
Foreign exchange rate forecasting is difficult, as its time series have complex nonlinear and nonstationary dynamics. To this end, the paper proposes a hybrid forecasting framework based on kernel regression decomposition that combines nonparametric trend extraction with linear and nonlinear forecasting models. In the framework we propose, we decompose each series of exchange rates into a long-run trend component and a short-run fluctuation component, which are modeled separately and then combined to generate forecasts. An empirical study based on five major foreign exchange markets shows that the proposed framework consistently outperforms conventional hybrid and standalone forecasting models in multiple forecasting accuracy measures. The statistical validation of the forecasting improvements is confirmed by the Diebold–Mariano test. Moreover, the decomposition offers an interpretable representation of exchange-rate dynamics by distilling persistent long-run movements from localized short-run nonlinear fluctuations. The results indicate that the proposed framework improves forecasting accuracy and offers insight into the structural behavior of foreign exchange markets.
Navigating success : unveiling the key predictors for firm growth and operational excellence
Coetzee, Rholé; Hall, J.H. (John Henry); Du Toit, Elda (Unisa Press, 2025-12)
PURPOSE : This study examines the key predictors of firm performance concerning growth opportunities and operational efficiency, both of which are crucial aspects of financial sustainability. DESIGN/METHODOLOGY/APPROACH : Using a dataset of 184 firms listed on the Johannesburg Stock Exchange (JSE) from 2011 to 2021, this study employs multiple linear regression modelling, part and partial correlation analysis, and percentage variance contribution analysis to identify the most significant predictors of firm performance. FINDINGS : The results indicate that the market-to-book value of equity is the strongest predictor of firm performance concerning growth opportunities, while return on equity is the most significant predictor of operational efficiency. These findings suggest that firms seeking to enhance financial sustainability should prioritise these metrics in strategic decision-making. RESEARCH/LIMITATIONS : This study focuses on JSE-listed firms, limiting the generalisability of the findings to firms in other regions or those that are not publicly listed. Future research could explore industry-specific variations and broader geographical contexts. PRACTICAL IMPLICATIONS : The findings offer valuable insights for corporate managers and investors. Firms can improve financial sustainability by focusing on strategies that enhance their market-to-book value of equity for growth and optimising return on equity to improve operational efficiency. ORIGINALITY/VALUE : This study contributes to the existing literature by systematically identifying and validating the strongest predictors of financial sustainability through rigorous statistical techniques. The results provide practical guidance for firms aiming to enhance growth and achieve operational excellence.
Exploring salient creditor perspectives on support for business rescue plans for decision-making
Kgobe, Beauty; Pretorius, Marius; Rosslyn-Smith, Wesley John (Unisa Press, 2025-12-16)
BACKGROUND : Creditors, especially banks, play a significant role during business rescue (BR) proceedings and in the sustainability of business operations after substantial implementation. The expectations by banks as influential secured creditors on the BR plans are still not refined and establishing the banks’ benchmark on the plans and what drives their decisions is essential. PURPOSE/OBJECTIVE : This study investigates what banks regard as good or bad plans and what critical information drives their decision to support or reject the plans. DESIGN/METHODOLOGY : Data were collected through semi-structured interviews with ten individuals within the banking industry who are within business support, workout, or a turnaround department. FINDINGS : The findings reveal the key information that banks, as salient stakeholders, consider critical in BR plans for decision-making. This information relies heavily on deal-breaker factors, clear prospects, the proposed strategy, and financier caveats. Furthermore, the findings show that there is a need for the framework of BR plans to be revisited. RESEARCH LIMITATIONS : Based on voting powers, creditors included secured creditors only excluding trade creditors and suppliers. Furthermore, literature on BR plans in South Africa was found to be limited. ORIGINALITY/VALUE : The study highlights the need for improved knowledge and upskilling business rescue practitioners (BRPs) as well as for accredited professional bodies to relook at minimum requirements for awarding BRP licenses. BRPs can use this information to understand what creditors are looking for and engage with creditors for pre-packaged plans. BRPs can understand the criteria that creditors consider in a BR plan for it to be a good BR plan, and what information they need to persuade them to vote for BR plans.
Green entrepreneurship research : a review of the domainand future research agenda
Fubah, Clavis Nwehfor; Kansheba, Jonathan Mukiza; Marobhe, Mutaju Isaack; Acikdilli, Gaye (Wiley, 2026)
This study examined the evolving landscape of green entrepreneurship (GE) research through a comprehensive analysis that combined bibliometric and systematic literature reviews. Analysis of 88 articles retrieved from the Web of Science (WoS) mapped the research trajectory, identifying key authors, journals and research themes. Findings revealed a growing interest in GE re-search, with a discernible shift toward six themes. The themes were drivers and motivators, pro-environmental behaviours (PEB)and practices, business models and strategies, entrepreneurial intentions and orientation and the crucial role of innovation and technology. Thus, we identified key gaps, with suggestions for future research directions. These included exploring the interplay between technology and green entrepreneurial activity, the impact of enabling policy frameworks and the influence of consumer behaviour driving green entrepreneurial activity. This study contributes to a more nuanced understanding of the GE field, pro-viding a strategic roadmap for future research endeavours.
The role of gender in telecommuting’s effect on employee engagement dimensions and employee performance: a moderated-moderation analysis
Ravhudzulo, Hangwani Raymond; Eresia-Eke, Chukuakadibia E. (Danubius International University, 2026-08-28)
In South Africa’s Information Communication Technology sector, where diversity manifests through differences such as race, culture, language, and socio-economic backgrounds, telecommuting offers unique possibilities for fostering inclusion and accommodating diverse workstyles. However, this potential must be understood in the context of gender, and its possible impact on employee engagement dimensions (physical, cognitive, emotional) and employee performance. Specifically, this study aims to contribute to the discourse on gender within the South African ICT sector, where telecommuting disparities and challenges remain critical. A study of 478 ICT employees used validated scales to measure telecommuting, employee engagement dimensions and employee performance. Using the PROCESS Macro technique in Smart-PLS 4, the study investigated the moderated-moderation relationship. The study’s findings indicate that gender moderates the telecommuting moderated relationship between emotional engagement and employee performance. In addition, the telecommuting moderating effect on the relationship between emotional engagement and employee performance varies with respect to gender. The study’s findings suggest that organisations should tailor their approaches to remote work and engagement strategies based on gender dynamics to optimize outcomes. This study is among the first to examine the moderated-moderation effects of gender on the telecommuting moderated relationship between employee engagement dimensions and performance in the context of the South African ICT sector.
Reclaiming leadership knowledge : decolonising the study of leadership in Africa
Matshoba-Ramuedzisi, Tumeka; Fourie, Willem (Sage, 2026-08)
Leadership studies have long been dominated by Western paradigms, often overlooking the diverse cultural, political, and socio-historical contexts that define leadership in Africa. Scholars have increasingly acknowledged the need to decolonise leadership studies, advocating for a more representative and inclusive approach that integrates African perspectives. Decolonisation in this context refers not only to addressing historical biases but also to creating frameworks that are rooted in African realities, traditions, and philosophies. This paper asks: to what extent has leadership scholarship moved beyond Western-centric frameworks to meaningfully integrate African perspectives? To address this question, 72 English-language, peer-reviewed articles on African leadership published between 2012 and 2022 were reviewed. The analysis reveals a growing, albeit uneven, engagement with African leadership paradigms, the enduring impact of colonialism, and the importance of integrating indigenous knowledge and philosophies such as Ubuntu into conceptualisations of leadership. Conceptual advances have consistently outpaced institutional and developmental change, and the field’s reliance on a small number of indigenous frameworks risks reproducing the reductive tendencies it seeks to displace. The study’s restriction to English-language publications also means that leadership perspectives from Francophone and Arabic-speaking Africa, including North Africa and the Maghreb, remain largely absent from the analysis. These findings contribute to ongoing scholarly debates on the decolonisation of leadership knowledge and offer an evaluative assessment of how far that effort has progressed. They also carry implications for cross-cultural management scholarship, which can only offer a fuller account of how leadership operates across cultural contexts by engaging African perspectives as independent sources of leadership knowledge.
Orchestrating transformative resilience in resource-constrained environments : a supply chain perspective
Essuman, Dominic; Agigi-Mocke, Assilah; Acquah, Ishmael Nanaba; Quansah, Emmanuel Kweku (Emerald, 2026)
PURPOSE : Resource-constrained environments both spur and hinder transformative resilience, yet little is known about how some firms navigate such environments to achieve transformative resilience. This study proposes and examines the presence of supply chain managers and supply chain entrepreneurial orientation as resource-orchestration enablers of transformative resilience in resource-constrained environments. DESIGN/METHODOLOGY/APPROACH : The study hypothesizes that the presence of supply chain managers and supply chain entrepreneurial orientation, individually and through their interdependent relationship, drive transformative resilience. The study's hypotheses are tested on survey data from 397 firms in a resource-constrained environment (Ghana). The findings are validated with 2nd-wave survey data on transformative resilience from 205 of these firms, collected a year later. A series of regression-based multivariate analyses is used to analyze the data. FINDINGS : The results indicate that, unlike the presence of supply chain managers, a strong supply chain entrepreneurial orientation accounts for high levels of transformative resilience. The contribution of supply chain manager presence to transformative resilience is mediated by supply chain entrepreneurial orientation. ORIGINALITY/VALUE : This study presents resource orchestration theory as a promising lens for conceptualizing transformative resilience and analyzing its building blocks from a supply chain perspective. It further addresses gaps in the empirical understanding of transformative resilience in terms of its measurement and antecedents.
Evaluation of parametric estimation methods for the gamma distribution using maximum likelihood and Bayesian approaches in a censored life-testing strategy with Markov Chain Monte Carlo simulations
Hesse, Christian Akrong; Boyetey , Dominic Buer; Kpeglo, Emmanuel Dodzi; Ashiagbor, Albert Ayi (Gnedenko Forum, 2025-03)
The goal of this study was to address the computational challenges associated with parametric estimation of the gamma distribution by evaluating the performance of the maximum likelihood and maximum a-posteriori estimation methods within the framework of Markov Chain Monte Carlo simulations. This was done by first assuming a censored life-testing strategy that terminates on the rth failure from a given sample of n electronic devices. Second, we obtained the joint distribution function of the first r-order statistic by arranging the r values in order of magnitude. Finally, we explored through the Markov Chain Monte Carlo framework using the maximum likelihood and maximum a-posteriori to estimate the gamma distribution parameters. The findings of this study suggest that both estimation methods were not significantly different from the actual hypothesized parameter values. Further, we observed that irrespective of the prior distribution used for the Bayesian maximum a-posteriori Markov Chain Monte Carlo estimation, the resulting parametric estimates of the gamma distribution remain the same, confirming the assertion that the Bayesian maximum a-posteriori Markov Chain Monte Carlo approach is a valuable tool for informative posterior analysis. The study’s uniqueness lies in adopting a censored life-testing strategy centered on the joint distribution function of the first r-order statistic.
Creating value through service innovation : an effectual design thinking framework
Schuld, Lindie; Antonites, Alex J.; Bornman, Dawid Alwyn Jacobus; Serfontein-Jordaan, Muriel (Pluto Journals, 2025)
Research reveals the disjointed nature of service innovation and an overall desertion in studies towards cumulative knowledge development. Studies also show a lack of focus on customers and employees as the fundamental resources for innovation and value creation. The purpose of this study is to investigate how service innovation can be more comprehensive, systematic and focused on the customer and employee resources of the firm. A constructivist paradigm directed this study’s research design and methodology. The investigative, qualitative research design incorporates an inductive and deductive approach and utilizes semi-structured interviews as the primary data collection method. Collected data were analysed with a predetermined coding frame by way of a phased thematic analysis process. The data analysed informed four constructs: focus, frame, function and forms –all essential to effective innovation and value creation. The four constructs were developed in a framework for service innovation and value creation that is oriented more towards the employee and customer, and one that is more comprehensive and systematic. The paper provides researchers and business managers with an enhanced understanding of how value is created through service innovation. The study’s purpose-driven, human-centred and means-enabled framework affords guidance, both in terms of the service innovation approach and its development process for value creation. The guidance and insights put forward may aid practitioners in their pursuit of service solutions with purpose, contribute to superior performance and have a sustainable impact.
Digitalisation in the procurement process of a water utility : a South African perspective
Ncanywa, Zisanda; Jojozi, Fani Nicholas; Eresia-Eke, Chukuakadibia E. (AOSIS, 2026-05-07)
ORIENTATION : Process digitalisation has been increasingly adopted as a strategic means of enhancing organisational performance. However, the digitalisation of inefficient processes risks perpetuating existing shortcomings by consistently delivering suboptimal results. Repetitive tasks are often default candidates for digitalisation, and some procurement tasks fall into this category. RESEARCH PURPOSE : Guided by four research questions, this study seeks to investigate the persistent bottlenecks arising from the entity’s reliance on manual practices in contract management, aiming to improve efficiency, transparency and overall process effectiveness. MOTIVATION FOR THE STUDY : Too often, procurement value is measured through cost savings, which are commonly achieved through sourcing and contracting. However, contract management remains a complex administrative task that is often disproportionately dependent on account managers for execution and oversight. This study investigates the digitalisation of the contract management task in the procurement process within a Water Utility in South Africa. RESEARCH DESIGN, APPROACH AND METHOD : A single-case qualitative research design was employed, using semi-structured interviews with key personnel involved in procurement activities within the selected entity. The data were thematically analysed to extract insights. MAIN FINDINGS : The findings reveal critical gaps in contract management, characterised by inefficiencies, inconsistencies and delays stemming from manual workflows. The study highlights that effective digitalisation requires not only technological adoption but also organisational readiness and supportive environmental factors. PRACTICAL/MANAGERIAL IMPLICATIONS : The digitalisation of the contract management task should be aligned with the organisation-wide digital strategy. Investing in digital infrastructure should be prioritised and supported by a skills audit and subsequent staff training. CONTRIBUTION/VALUE-ADD : This study contributes by revealing contract management gaps driven by inefficient, inconsistent manual workflows, and shows that successful digitalisation requires both technology adoption and organisational readiness with supportive environmental conditions.
Making sense of sustainability : a decade of research and emerging directions for the future
Monkge, Tshegofatso Alice; Le Roux, Catherine Anne; Letsholo, Rebaona Gladness (AOSIS, 2026-05-26)
ORIENTATION : Corporate sustainability is an evolving construct shaped by multiple interpretations and contextual meanings. This plurality affects managerial action and underscores the need for studies to deepen theoretical and practical understanding. RESEARCH PURPOSE : This study aims to synthesise the scholarly debate through a structured scoping review at the intersection of sensemaking and corporate sustainability. The systematic synthesis of a decade of scholarship provides a firmer conceptual grounding for future research. MOTIVATION FOR THE STUDY : Despite growing interest, research at the intersection of organisational sensemaking and corporate sustainability remains fragmented and conceptually underdeveloped. This study addresses this gap by mapping thematic patterns, identifying silos, and exposing overlooked perspectives. RESEARCH DESIGN, APPROACH AND METHOD : Based on 104 peer-reviewed articles (2014–2024), this structured scoping review uses thematic analysis and bibliometric techniques to trace the field’s evolution, drawing on Scopus and ScienceDirect for cross-disciplinary synthesis. MAIN FINDINGS : Three dominant thematic clusters around which sensemaking processes in corporate sustainability are articulated are revealed: (1) Responsibility, (2) Leadership, and (3) Strategy. An integrative conceptual framework is proposed, offering an interpretive lens to advance practice and future scholarship. The findings expose conceptual silos and underexplored empirical contexts as avenues for future research. PRACTICAL/MANAGERIAL IMPLICATIONS : Management could utilise the study’s findings to provide actionable insights for aligning strategic intent with sustainable practice, especially in conditions of ambiguity. CONTRIBUTION/VALUE-ADD : By presenting a framework that uncovers corporate sustainability interpretations in practice, the study not only advances scholarship in an underexplored domain but also highlights key theoretical tensions and outlines a future research agenda.
Stories of grit and grace : sociocultural pathways to success in township entrepreneurship
Mathebula, Veronica; Moos, Menisha; Crafford, Anne (World Scientific Publishing, 2026-06)
Entrepreneurship in South Africa’s townships is frequently examined through deficit-based lenses that emphasize poverty and infrastructure constraints, with less attention given to the sociocultural factors that sustain entrepreneurial success. Addressing this gap, this study explores how sociocultural factors facilitate and constrain successful township entrepreneurs in Gauteng, South Africa. Drawing on social network theory and a qualitative multiple-case narrative design, life story interviews were conducted with six established township entrepreneurs. The findings develop a contextually grounded typology of five interrelated sociocultural factors shaping entrepreneurial success: family, friends and other reference groups, culture, religion and political history. These factors generate multiple forms of capital, including relational, symbolic, spiritual and institutional resources, which entrepreneurs mobilize to access opportunities, build legitimacy, sustain resilience and create community effect. However, the findings also reveal the ambivalent nature of embeddedness, as the same networks that provide support may impose obligations and dependence. The study contributes to entrepreneurship scholarship in two ways. First, it offers a typology of sociocultural capital relevant to township economies. Second, it extends social network theory by showing that entrepreneurial networks in historically marginalized contexts are shaped not only by economic exchange but by identity, meaning-making and transcendent relationships. The article advances context-sensitive theorizing and offers practical insights for entrepreneurship development in townships and other Global South settings.
Unlocking shared value : reimagining multi-stakeholder collaboration for future-oriented post-school skills development
Selebi, Olebogeng; Ngwenya, Thembinkosi (Emerald, 2026-12-14)
PURPOSE : This study investigates how multi-stakeholder partnerships (MSPs) support skills development in the post-school education and training sector. It examines how MSPs enhance alignment between education systems and labour market needs within rapidly shifting economic and technological contexts. DESIGN/METHODOLOGY/APPROACH : Drawing on social systems and stakeholder theory, the study used 24 semi-structured interviews with senior system-level and leadership stakeholders across government, higher education, civil society, and industry. The qualitative, interpretivist approach extends global MSP literature by foregrounding coordination practices in a Global South setting. FINDINGS : Five themes emerged: stakeholder complementarity, strategic communication, institutional alignment, partnership sustainability, and shared visions of quality education. Although MSPs were widely valued, challenges included policy misalignment, unclear roles, and uneven engagement. RESEARCH LIMITATIONS/IMPLICATIONS : The sample reflects senior perspectives within one national context, excluding frontline educators and students. Future work should include longitudinal and mixed-methods designs to enhance applicability and incorporate a wider range of stakeholder voices. PRACTICAL IMPLICATIONS : Clearer role definition, stronger communication frameworks, curriculum-labour market alignment, and improved collaborative structures are recommended. SOCIAL IMPLICATIONS : Strengthened MSPs can support inclusive, future-oriented skills ecosystems that advance employability and socio-economic development. ORIGINALITY/VALUE : The study offers a systems-level perspective of MSPs as interdependent, intentionally structured arrangements. It contributes to global scholarship by identifying conditions that strengthen labour market alignment and skills pipeline coherence in resource-constrained contexts.
A thematic analysis of how small and medium-sized enterprises experience and adapt to exogenous shocks in Africa : a case study on anglophone countries
Zwane, Princess Nkambule; Moos, Menisha (Adonis and Abbey Publishers, 2026-03-01)
Research has extensively investigated how exogenous shocks (ES) affect small and medium-sized enterprises (SMEs). However, insights into how SMEs in Anglophone African countries experience and adapt to ES remain limited. This study reviewed the literature on SMEs and ES in Anglophone Africa, identifying the main themes and issues examined in this area over the past decade (2014-2024). The Scopus and Google Scholar databases were searched for research articles, and 38 articles were selected for analysis. A qualitative research approach was used, including an in-depth literature review and thematic analysis to uncover key themes and subthemes. The study found that SMEs in Anglophone Africa experience ES both negatively and positively. Their adaptive strategies to ES included innovation, pivoting, networking, and digitalisation. These findings align with elements identified in the literature. This study delineates critical research gaps in the intersection of SMEs and ES, providing nuanced insights from the Anglophone African perspective regarding SMEs’ experiences and their adaptive mechanisms to ES. Practically, these findings can assist policymakers in developing targeted interventions, avoiding a blanket approach, and enabling Anglophone African SMEs to make more informed decisions that enhance resilience and preparedness for future shocks.
Middle managers' sensemaking and sensegiving practices in a hybrid work context
Jimmy, Keeanne; Le Roux, Catherine Anne (JCMAN, 2025)
PURPOSE : Middle managers play a crucial role in interpreting and communicating organisational strategy, particularly in hybrid work environments where strategic objectives must be continuously adapted to operational realities. While existing research recognises their strategic influence, few studies explore middle managers' sensemaking and sensegiving practices within hybrid contexts. This study addresses this gap by exploring how middle managers navigate the complexities of a hybrid work environment to facilitate strategy transmission. DESIGN/METHODOLOGY/APPROACH : A qualitative case study was conducted within a large South African FMCG company. Data was collected through 12 semi-structured online interviews with middle managers from various business units. The study was guided by two research questions: (1) How do middle managers make and give sense within hybrid work contexts? (2) What practices are utilised by middle managers to interpret and transmit the strategy message? FINDINGS : Middle managers in the hybrid work context demonstrated how they transmitted strategic directives and recalibrated their actions. Sensemaking practices included re-establishing work boundaries, managing productivity perceptions, and leveraging informal communication networks. Key sensegiving practices included rephrasing strategic messages, personalising engagement, and fostering accountability. While digital tools support communication, in-person interactions remain essential for relational depth and strategic clarity. These findings offer insight into the situated micro-practices that bridge strategic intent and everyday work in a disrupted and evolving work environment. PRACTICAL IMPLICATIONS : The findings demonstrate the centrality of middle managers as meaning-makers and extend our understanding of how strategy work is performed under conditions of fluidity. To enhance strategic alignment, organisations should support middle managers by formalising hybrid work policies that balance digital and in-person collaboration. Management can use these practices to strengthen engagement, job crafting, work-life balance, and trust, thereby ensuring clarity in strategy execution.
Evaluating the role of consumer and business confidence in petroleum consumption
Das, Sonali; Phadi, Nteboheng Pamella (Inderscience, 2026-05-11)
Although organisations actively invest in technologies designed to capture customer data, the ability to translate this data into insight that is reflective of concurrent supply chain dynamics can be a non-trivial exercise. We examine both domestic capabilities, and global drivers, of the petroleum supply chain and undertake two investigations: 1) at the macro-level, we use secondary-data to investigate predictive models for consumption of petrol and diesel, both of which are directly and indirectly influenced by various local and international factors; 2) at the micro-level, we administered a tailored-questionnaire at a petroleum company to investigate any missing link between their supply-chain and their customer demand-chain with regards to three aspects namely, people, process and technology, which were then analysed within the structural equation model framework. Overall, the study provides valuable insights for future research aimed at better integration of customer sentiment and supply chain data analytics for petroleum procurement and planning.
Hybrid approaches to forecast daily average PM₂.₅ concentrations : an application to the Brazilian state of Minas Gerais
Da Silva, Kim Leone Souza; Iftikhar, Hasnais; Rodrigues, Paulo Canas (Taylor and Francis, 2026)
The human impact on the planet is evident, and the need to mitigate these effects is becoming increasingly urgent. Air pollution, for instance, is inextricably linked to both the environment and human health. Particulate matter with diameters smaller than 2.5 micrometers, known as PM₂.₅, can have a severe impact on human health due to its ability to penetrate the respiratory system. The objective of this study is to forecast PM₂.₅ concentrations at monitoring stations within the Brazilian state of Minas Gerais. Hybrid models were developed to improve predictive performance by combining parametric, nonparametric, and neural network approaches for particulate matter forecasting. The results indicate that the proposed hybrid models perform competitively across various time horizons. These findings underscore the importance of combining different modeling approaches, leveraging each method's strengths to capture complex patterns and improve forecast accuracy. Furthermore, integrating parametric, nonparametric, and neural network techniques enables more robust, flexible modeling that can adapt to diverse temporal patterns and data characteristics. The methods developed in this study show promise and contribute to the advancement of research on air pollution in Brazil by providing a comparative analysis of the performance of forecasting models applied to different municipalities in Minas Gerais.
Functional time series modeling of traffic flow : a probabilistic approach to temporal symmetry
Jan, Faheem; Iftikhar, Hasnain; Gul, Naveed; Almuhayfith, Fatimah E.; Rodrigues, Paulo Canas (MDPI, 2026-05)
Reliable short-term traffic flow prediction is crucial for intelligent transportation systems to enable real-time control, mitigate congestion, and improve urban mobility. However, traffic dynamics are inherently uncertain, temporally dependent, and subject to pronounced intraday variability, making accurate forecasting challenging. To address these issues, this study introduces a Functional AutoRegressive (FAR) model that represents daily traffic profiles as continuous stochastic functions rather than discrete observations, thereby preserving temporal continuity and capturing underlying symmetric structures. The model is developed using high-frequency traffic data collected at 15-min intervals from the Dublin Airport Link Road, Ireland, covering January 2022 to December 2024; data from 2022–2023 are used for model estimation, while 2024 data are reserved for one-day-ahead out-of-sample evaluation. A moving-window filtering technique is incorporated to enhance robustness by probabilistically identifying outliers and reducing noise. The proposed FAR approach is benchmarked against conventional models, including autoregressive (AR), autoregressive moving average (ARMA), nonparametric autoregressive (NPAR), and vector autoregressive (VAR) models. Empirical results demonstrate that the FAR model consistently achieves superior forecasting performance across all traffic conditions, yielding a full-day MAPE of 9.160% compared to 11.623% for the VAR model, along with lower MAE (76.772) and RMSE (131.767). It also performs best on both workdays and weekends, with MAPEs of 8.129% and 10.438%, respectively. Moreover, the model remains robust across peak and off-peak periods, effectively capturing both symmetric and asymmetric traffic variations while offering a more interpretable representation of intraday patterns. These findings suggest that functional time series modeling provides an effective and computationally efficient framework for traffic forecasting, with strong potential for application in next-generation intelligent transportation systems.
A decomposition-driven hybrid approach to forecasting oil market dynamics
Dar, Laiba Sultan; Abdelwahab, Mahmoud M.; Aamir, Muhammad; Rind, Moeeba; Rodrigues, Paulo Canas; Abdelkawy, Mohamed A. (MDPI, 2026-03)
Modeling nonstationary time series in financial and energy markets remains challenging due to nonlinear dynamics, volatility clustering, and frequent regime shifts that distort the underlying probabilistic structure of the data. This study introduces a novel probabilistic–statistical decomposition framework, termed Robust Adaptive Decomposition (RAD), designed to preserve probabilistic symmetry between deterministic and stochastic components. In this context, symmetry refers to maintaining statistical balance—particularly in the means, variances, and distributional structures—between the extracted modes and the residual series, thereby preventing artificial bias or variance distortion during decomposition. The RAD framework adaptively determines the optimal number of modes needed to effectively separate short-term fluctuations from long-term structural movements. Unlike conventional techniques, such as Empirical Mode Decomposition (EMD), Ensemble EMD (EEMD), and CEEMDAN, the proposed method incorporates a robustness mechanism that mitigates mode mixing and reduces distortions induced by extreme shocks and regime transitions. The empirical evaluation is conducted on six oil-related energy commodities—Brent crude oil, kerosene, propane, sulfur diesel, heating oil, and gasoline—whose price dynamics exhibit pronounced nonlinearity and structural volatility. When integrated with ARIMA forecasting models, the RAD-based framework consistently outperforms benchmark decomposition approaches. Across all datasets, RAD–ARIMA achieves reductions of approximately 65–90% in MAE, 60–85% in RMSE, and up to 95% in MAPE relative to CEEMDAN-based models. These results demonstrate that RAD provides a mathematically rigorous and computationally efficient preprocessing mechanism that preserves statistical equilibrium while effectively disentangling deterministic structures from stochastic noise. Beyond oil markets, the framework offers broad applicability in econometric modeling, financial forecasting, and risk management, contributing to probability- and statistics-driven symmetry analysis in complex dynamic systems.

Browse

Recent Submissions