Regression Decomposition Research Articles

Can companies' input of data factor eliminate investors' home biases?

Data as a new production factor plays an increasingly crucial role in influencing investor decision-making. This paper investigates how the data factor input, measured using a two-stage regression decomposition approach, impacts investors' home biases. Analyzing a sample of Chinese listed companies from 2012 to 2022, we find that: 1) companies' input of data factor effectively reduces investors' home biases; 2) this reduction is primarily driven by a decrease in information asymmetry; 3) the mitigating effect of data factor input is further strengthened by external factors such as heightened attention from analysts and stronger corporate governance. Additionally, our results reveal that this mitigating effect is more pronounced among companies facing high financing constraints, possessing low reputations, operating in low-technology industries, or located in regions with underdeveloped digital financial infrastructure. These findings offer new insights into underscore the critical role of data factor in shaping capital markets.

Statistical analysis of the impact of profitability in the manufacturing and service sectors on the UK Economy’s Growth

The UK economy's performance is closely tied to the profitability of its Manufacturing Sector (MS) and Service Sector (SS). Understanding these sectors' dynamics is crucial for effective policymaking. Integrating sustainable practices in both sectors enhances profitability and operational efficiency while contributing to economic growth and reducing environmental impact. This study investigates the relationship between UK economic growth and profitability in the MS and SS from 1998 to 2022. The primary objective is to examine how profitability influences the UK's growth trajectory. Employing various statistical methods, including correlation, regression, cointegration, and variance decomposition analyses, the study aims to provide insights into the interplay between GDP and sector profitability. A quantitative approach using secondary data on GDP and profitability from reliable sources is adopted. Correlation analysis explores relationships between these variables, while regression analysis assesses the impact of MS and SS profitability on GDP. Cointegration tests identify long-term equilibrium relationships, and variance decomposition analysis reveals the variability of GDP and sector profitability over time. The correlation matrix indicates positive associations between GDP and both sectors, with the SS showing a stronger correlation. Regression analysis confirms significant effects of both sectors on GDP, with the SS exerting a positive influence and the MS a negative impact. Cointegration tests highlight long-term stability, and variance decomposition analysis emphasizes the dynamic nature of these relationships. This study elucidates the intricate link between UK economic growth and sector profitability, underscoring the SS's critical role in driving expansion while addressing challenges in the MS. Policy recommendations include enhancing productivity and innovation in both sectors, informed by evidence-based decision-making. Overall, the study contributes valuable insights into the UK economy's growth dynamics, guiding sustainable economic development strategies.

Rural-urban differentials in undernutrition among women in India: Evidence from a decomposition approach.

Background: Global healthcare and nutrition policies have not eliminated the pressing public health issue of undernutrition, which remains a paramount public health concern in countries like India, coinciding with overweight and obesity, in the form of dual burden of malnutrition. Aim: This study delves into the rural-urban differential in undernutrition among reproductive-aged women in India for targeted policy interventions and to achieve universal health coverage. Methods: Data from the recent iteration of the National Family Health Survey (NFHS-5; 2019-21) were utilized to examine the factors influencing rural-urban differentials in women's undernutrition. A set of logistic regression and Fairlie's decomposition analysis are employed to identify the associated covariates and understand the factors driving these differentials. Results: The analysis reveals that rural women are significantly more vulnerable to undernutrition compared to urban counterparts, with factors such as education, wealth status, age, and dietary diversity playing key roles. The decomposition analysis of the rural-urban gap revealed that the variables considered in the study accounted for approximately 75% of the disparity. The difference in household wealth between rural and urban areas contributed about 63% of the explained gap, followed by educational status (16%), age group (11%), dietary diversity (8%), religion (5%), and media exposure (4%). Conclusion: The findings underscore the importance of targeted interventions addressing socio-economic inequalities to mitigate undernutrition among women in India. Enhancing access to education, improving economic opportunities, promoting dietary diversity, and challenging cultural norms are crucial steps towards achieving equitable nutritional outcomes and reducing the existing rural-urban disparity.

Interannual moisture variability on the Qinghai Plateau: Trends, patterns, and implications

Investigating surface dry-wet patterns on the Qinghai Plateau (QP) is crucial for water allocation, ecological sustainability, and climate variability adaptation strategies. Existing discrepancies in the QP dry-wet trends and distribution characteristics underscored the need for a more refined analysis. This study utilized the Thornthwaite Moisture Index (IM) to quantify changes in surface dryness and wetness under prevailing climatic conditions. Linear trend regression and ensemble empirical mode decomposition (EEMD) were applied to study the dynamic and periodic characteristics of the QP from 1980 to 2018.Our findings revealed a decrease from southeast to northwest in IM, with the semi-arid and sub-humid transition line aligning closely with the 400 mm isohyet. The dry-wet transition line exhibited a northwestward trend over the past four decades. Possibly influenced by monsoon circulation and El Niño-Southern Oscillation (ENSO), the annual IM displayed a quasi-cycle of 3 to 5 years, manifested by a dry period (1990–2004) and a wet period (2005–2012). However, spatial differences existed, challenging the universality of the “Dry gets Drier and Wet gets Wetter (DDWW)” pattern. Precipitation (PRCP) changes could predict over 90 % of IM spatiotemporal variations. Additionally, the IM response to Average Temperature (TAVG) exhibited an inverted U-shaped curve, with a boundary (−3.8 °C) below which cooler regions became wetter and above which they became drier. The observed warming and precipitation shifts suggested that continued warming could lead to warmer and wetter climates, potentially causing ecological and environmental problems. Therefore, examining the surface moisture budget is of critical scientific and practical significance, in order to provide a decision-making basis for mitigating and adapting to climate change.

The interaction between Indigenous identity and rural residency in dementia prevalence among Ecuadorian older adults.

While recognizing the acknowledged difference in dementia prevalence between Indigenous and non-Indigenous populations, most previous studies were conducted in the Global North. This study aims to examine the relationship between Indigenous ethnic identity and dementia status with a special focus on urban-rural differences among older adults in Ecuador. Data came from Ecuador's Survey of Health, Welfare, and Aging (SABE), derived from a probability sample of households in Ecuador. The final sample comprised 4,984 adults aged 60 or older. Dementia status was assessed through three indicators: low scores on a cognitive assessment, the number of difficulties in instrumental activities of daily living (IADL), and self-reported dementia diagnosis. Logistic regression and multivariate decomposition analyses were utilized. Indigenous participants, even after adjusting for sociodemographic and health-related factors, exhibited a higher likelihood of having dementia compared to their non-Indigenous counterparts. Among Indigenous participants, those residing in rural areas had higher likelihood of having dementia status, while there was no significant urban-rural difference observed among non-Indigenous participants. Rural residency and covariates explain 91.0% of the observed difference in dementia prevalence between Indigenous and non-Indigenous older adults. Indigenous older adults who are living in rural areas are at particularly high risk of having dementia largely because they have presently recognized modifiable risk factors. These findings underscore the urgent need to prioritize provisions of appropriate and equitable service related to dementia for Indigenous People living in rural areas outside high-income countries.

Has socioeconomic inequality in perceived access to health services narrowed among older adults in China?

ObjectiveTo analyze the degree, evolution and causes of socioeconomic inequality in perceived access to health services among the older adults in China.MethodsThe data used in this study were drawn from the 4 waves of the Chinese Longitudinal Healthy Longevity Survey (CLHLS) in 2008, 2011, 2014, 2018. Erreygers index (EI) was used to measure socioeconomic inequality in perceived access to health services in each survey wave. A panel logit regression model was used to examine the impact of socioeconomic status on perceived access to health services. The recentered influence function (RIF) regression decomposition method was used to explore the causes of socioeconomic inequality in perceived access to health services. Inverse probability weighting (IPW) was employed to adjust estimates for missing responses and loss to follow-up.Results“Pro-rich” socioeconomic inequality in perceived access to health services in China was found with inequality falling through time. The older adults with higher incomes, who had adequate financial support, and those who were wealthier compared with other residents reported lower socioeconomic inequality in perceived access to health services. Having basic health insurance and access to care resources when ill can help alleviate such inequalities.ConclusionsSocioeconomic inequality in perceived access to health services was shown to be responsive to policies that enhance health insurance coverage and support the provision of (paid and unpaid) caregiving for the older adults.

A hybrid approach for power quality event identification in power systems: Elasticnet Regression decomposition and optimized probabilistic neural networks

The transformation of traditional grid networks towards smart-grid and microgrid concepts raises many critical issues, and quality in the power supply is one of the prominent ones that needs further research. Developing and applying power quality (PQ) recognition methods with efficient and reliable analysis are essential to the fast-growing issues related to modern smart power distribution systems. In this regard, a hybrid algorithm is proposed for PQ events detection and classification using Elasticnet Regression-based Variational Mode Decomposition (ER-VMD) and Salp Swarm Algorithm optimized Probabilistic Neural Network (SSA-PNN). The Elasticnet Regression (ER) process is suggested to modify the conventional VMD approach instead of the Tikhonov Regularization (TR) method to enhance performance and obtain better band-limited intrinsic mode functions. This idea results in robust and effective reconstruction features and helps to obtain accurate classification using the classifier. In the classification stage, a Salp Swarm Algorithm (SSA) based PNN is used for the PQ event, considering the relevant features obtained from ER-VMD. The system parameters often influence PNN performance, and SSA is used to determine the ideal values to improve the PNN's capacity for more accurate classification. The numerical values of the accuracy percentage, percentage of sensitivity, and percentage of specificity in the case of real-time data are found as 98.58, 100, and 98.46, respectively. The acquired comparison findings demonstrate the effectiveness and robustness of the proposed technique in terms of rapid learning speed, smaller computational complexity, robust performance for anti-noise conditions, and accurate identification and categorization.

Quantile regression decomposition analysis of disparity research using complex survey data: Application to disparities in BMI and telomere length between U.S. minority and white population groups

Quantile regression decomposition analysis of disparity research using complex survey data: Application to disparities in BMI and telomere length between U.S. minority and white population groups

Understanding period product use among young women in rural and urban India from a geospatial perspective

Ensuring proper menstrual hygiene management remains a significant challenge for young women in India. The term "exclusive use of hygienic period products during menstruation" refers to relying solely on period products like sanitary pads, tampons, or menstrual cups. Poor menstrual hygiene practices not only increase the risk of reproductive tract infections but also lead to various negative health outcomes, including discomfort and potential complications. This study explores factors associated with the exclusive use of period products during menstruation aged 15–24, investigates geographic disparities, examines rural–urban gaps, and assesses inequality in India. Utilizing data from the fifth National Family Health Survey (NFHS-5), responses from 2,41,180 women aged 15 to 24 were analysed using logistic regression and multivariate decomposition analyses to explore socioeconomic predictors. Moran's I statistics also assessed spatial dependency, while Lorenz curves and Gini coefficients measured inequality. Quintile and LISA maps visualized regional disparities. The study found that 76.15% of women in India reported exclusive use of hygienic period products during menstruation. Rural areas reported a lower percentage of exclusive use of hygienic period products (72.32%) during menstruation compared to urban areas (89.37%). Key factors associated with the exclusive use of hygienic period products among 15–24-year-old women in India include age, education, place of residence, wealth, access to media, and healthcare discussions. Geographically, central districts exhibited the lowest coverage (< 65%), while the Southern region reported the highest (> 85). The GINI coefficient of 0.39 highlighted moderate inequality in distribution. Decomposition analysis revealed that household wealth contributed 49.25% to rural–urban differences, followed by education (13.41%), media access (7.97%), and region (4.97%). This study highlights significant regional disparities and low utilization of hygienic period products among young women in India, particularly in central districts. Policymakers should prioritize interventions targeting these regions, addressing socio-economic disparities. Strategies to promote education, improve media access, and enhance household wealth can facilitate menstrual hygiene adoption. Initiatives to reduce sanitary napkin costs and increase accessibility, particularly in rural areas, are crucial to mitigating geographical disparities nationwide.

Decomposition of the wealth gradient in maternal healthcare quality in low- and middle-income countries

Although access to health services by poor populations has improved in most low- and middle-income countries, wealth remains associated with better quality of care that in turn leads to better health outcomes. Understanding the patterns of such inequities can inform the design of policies to improve services received by poor populations. We employ regression and inequality decomposition analyses using household survey data from 58 low- and middle-income countries between 2010 and 2021 to characterize inequity in quality of antenatal care, to test at which levels inequity exists, and to assess at which levels inequities are most pronounced. We find that in most countries and in both rural and urban areas, wealthier women are more likely to receive high-quality antenatal care than their poorer peers who reside in the same locality (village or neighborhood), even when attending similar types of health facilities (public vs. private, and primary care facilities vs. hospitals). However, although inequity exists at such a local level, most of the wealth gradient in quality of antenatal care is explained by variation in quality of care between wealthier and poorer localities.

On function-on-function linear quantile regression

We present two innovative functional partial quantile regression algorithms designed to accurately and efficiently estimate the regression coefficient function within the function-on-function linear quantile regression model. Our algorithms utilize functional partial quantile regression decomposition to effectively project the infinite-dimensional response and predictor variables onto a finite-dimensional space. Within this framework, the partial quantile regression components are approximated using a basis expansion approach. Consequently, we approximate the infinite-dimensional function-on-function linear quantile regression model using a multivariate quantile regression model constructed from these partial quantile regression components. To evaluate the efficacy of our proposed techniques, we conduct a series of Monte Carlo experiments and analyze an empirical dataset, demonstrating superior performance compared to existing methods in finite-sample scenarios. Our techniques have been implemented in the ffpqr package in .

Co-movement of Oil and Stock Markets During COVID-19: Evidence from the Gulf Corporation Council

This study aims to document the impact of oil price variations on generating stock returns in Gulf Cooperation Council (GCC) markets during the COVID-19 era. It documents the pandemic era results from January 2020 to October 2022 by employing cointegration, Granger causality, and time-varying coefficient-vector autoregression techniques on daily data. The findings suggest two-way causality between all stock indices and the oil market. Time-dependent relationships were observed during the review period. The findings (based on regression and variance decomposition) indicate that although the reliance of the GCC stock markets was not on oil alone, oil had a significant impact during the study period. It is recommended that investors not consider diversifying portfolios in GCC stocks and oil markets to optimize benefits. The findings are expected to enhance the understanding of academics, market players, regulators, and investors regarding relationships among GCC stocks and oil markets. This study contributes to the literature by documenting the impact of the oil market on stocks during an abnormal period of the COVID-19 pandemic, considering time-varying parameters in a net oil exporting region.

A decompositional analysis of social group inequality in India

ABSTRACT Using the national representative Indian household surveys collected by the National Sample Survey Organization, we examine the welfare gaps across social groups for the entire distribution in 1983, 1993–94, 2004–05 and 2011–12. We use spatially adjusted per capita consumption expenditure as the measure of welfare and show that there exists significant welfare gap between Scheduled Tribes/Scheduled Castes (ST/SC) and General Category (GC) households at higher quantiles of the distribution, but the magnitude of the gap has declined over the years for the SC households. Using unconditional quantile regression decomposition, we find that the coefficient effect (unexplained effect) dominates the endowment effect (explained effect) in explaining the gap in all four years. Further decomposition shows that the difference in educational distribution between the SC/ST and GC households drives most of the explained differences between the social groups.

Understanding the factors behind racial and ethnic disparities in the adoption of alternative financial services: a decomposition analysis

PurposeThe purpose of this study was to examine racial/ethnic differences in AFS use and their contributing factors using a decomposition analysis.Design/methodology/approachThe 2018 National Financial Capability Study dataset was used to analyze the four major types of AFS—title loans, payday loans, pawnshops, and rent-to-own (RTO) stores—as proxies for AFS use. The study conducted both logistic regression analysis and decomposition analysis to examine the contributing factors.FindingsThe results of the logistic regression analysis demonstrated significant disparities in the use of alternative financial services (AFS) among racial and ethnic groups. Specifically, it was found that Blacks were more likely to utilize title and payday loans, pawnshops, and rent-to-own (RTO) stores compared to Whites. In contrast, Hispanics and Asians/individuals of other ethnicities were less likely to use title loans, but Hispanics were more likely to opt for payday loans over Whites. Furthermore, objective financial literacy exhibited a negative association with the likelihood of using these four types of AFS, whereas subjective financial literacy consistently showed a positive association. When examining the decomposition analyses, it became evident that both objective and subjective financial literacy played significant roles in explaining the racial and ethnic disparities in AFS usage. However, the patterns varied in three specific pairwise comparisons.Originality/valueThis study revealed the relative contributions of each factor to the racial/ethnic disparities through decomposition analysis. Our Fairlie decomposition approach addressed non-linearities within the decomposition framework, particularly in estimating the probabilities of AFS utilization, given its binary outcomes. This extension builds upon the Oaxaca decomposition. The study offers valuable insights into the variations in AFS use among different racial and ethnic groups.

Academic or vocational education? A comparison of the long-term wage development of academic and vocational tertiary degree holders

Education is a key determinant of wage development. The relationship between education and wages is particularly strong in countries with vocationally oriented educational systems and a clear distinction between general and vocational education, such as Germany and Switzerland. However, whether general and vocational education offer the same returns to education is an ongoing debate. Previous findings from international research are still inconclusive. Against this background and based on theoretical arguments from human capital and signalling theory and the task-specific learning-by-doing approach, our paper examines the long-term wage development of Swiss university and professional education degree holders from the time they obtain their tertiary degree until their late career. It asks how differences between the two groups in wage development may be explained. Our results, produced with regression decomposition methods, show that within the first 20 years after graduation, university degree holders experience steeper wage growth. An important reason for this difference is that university graduates move more often than vocational tertiary degree holders into well-paid labour market positions endowed with formal authority, management responsibility, and a large proportion of cognitive nonroutine tasks.

Panel Data Regression and Index Decomposition Analysis of Greenhouse Gas Emission in Regional Local Governments

Panel Data Regression and Index Decomposition Analysis of Greenhouse Gas Emission in Regional Local Governments

Education and non-communicable diseases in India: an exploration of gendered heterogeneous relationships.

While the association between education and non-communicable diseases (NCDs) is well established, it remains unclear whether this association varies by gender. The aim of this study was to examine two critical research questions: whether the association of education and NCDs is conditioned by gender and, if so, what are the factors contributing to this? Data from the Longitudinal Aging Study in India Wave 1 (2017-2018) was used for the empirical analysis. The study employs bivariate, binary logistic regression and Oaxaca decomposition analyses. The results reveal that the net likelihood of having at least one chronic NCD increases with an increase in education level for men (<5y of schooling: odds ratio [OR] 1.18 [95% confidence interval {CI} 1.09 to 1.28]; ≥10y of schooling: OR 1.43 [95% CI 1.33 to 1.53]). However, for women, the result showed a contrasting pattern. The decomposition analysis revealed that the distinctive roles of marital status and working status in the diagnosis of morbidity for men and women are the key factors behind the gendered heterogeneous relationship of education and NCDs in India. The study found that it is important to acknowledge the potential impact of self-reporting bias in morbidity data while examining the relationship between education and NCDs.

The Impact of Access to Intermediate Inputs on Export Margins: Firm-Level Evidence from the Regression Decomposition Approach

This paper analyzes how export margins responded to an intermediate input supply shock caused by the 2020 lockdown in China. We use regression decomposition with triple and quadruple difference-in-differences models to identify causal impacts and mitigate potential heterogeneity in transaction-level customs data from the Bangladesh apparel manufacturing industry. The triple difference estimate shows that the average export value per firm–product–destination combination declined by approximately 65%, leading to a decrease in overall exports of woven apparel from Bangladesh. The input supply shock also adversely affected the subgroups of firms across various firm-level characteristics along the intensive margin. Moreover, the export market share decomposition reveals that the shock significantly affected intensive margins by decreasing incumbents’ market allocation by 9%. An equivalent increase in extensive margins led to a readjustment in the market allocation, leading to fewer market leavers and slightly more new market entrants. Our results indicate that Bangladesh’s exports mostly decreased due to the smaller quantities of products exported rather than there being fewer firms, destinations, or products involved in export trade. There were significant market share reallocations that occurred after the Chinese input supply shock. An appropriate policy stance is required for sustainable export sector growth strategies, which will enhance the country’s defense against potential future shocks and foster the achievement of sustainable development goals (SDGs) in Bangladesh.

Spatial distribution of benthic taxonomic and functional diversity in the Yellow River Basin: From ecological processes to associated determinant factors

One of the fundamental objectives in ecology is to investigate the ecological processes and associated factors governing the abundance and spatial distribution patterns of biodiversity. However, the reaction of biological communities to environmental degradation remains relatively unknown, even for ecologically crucial communities like macroinvertebrates in aquatic ecosystems. Here, we sampled 117 locations to quantify relative contributions of geographical and environmental factors, including water quality, land use, climate, and hydrological factors, to determine the absolute and relative compositions of macroinvertebrate communities and their spatial distribution in the Yellow River Basin (YRB), the sixth-longest river system on Earth. We assessed relative roles of species sorting and dispersal in determining macroinvertebrate community structure along YRB. Our results demonstrated that alpha and beta diversity indices showed an increase from the up- to low-reaches of YRB. The middle and low-reaches exhibited elevated species diversity and both regions exhibited relatively stable community compositions. The biodiversity of macroinvertebrates was influenced by a combination of geographical factors and environmental variables, with environmental factors predominantly serving as the principal determinants. Results of multiple linear regression and variance decomposition showed that the effect of environmental factors was approximately three times greater than that of spatial factors. These findings provide support for the hypothesis that species sorting, driven by environmental gradients, plays a significant role in shaping the community structure of macroinvertebrates in running water ecosystems at the basin scales. Moreover, the factors contributing to substantial shifts in biodiversity across different segments of YRB indicate that distinct river sections have been influenced by varying stressors, with downstream areas being more susceptible to the impacts of water pollution and urbanization resulting from human activities.

Gradients in low birthweight by maternal education: A comparative perspective

BackgroundLongstanding research has shown strong inequalities in low birthweight by household income. However, most such research has focused on Anglophone countries, while evidence emerging from other developed countries suggest a stronger role of education rather than incomes in creating inequalities at birth. This paper compares gradients in low birthweight by maternal education, as well as explores underlying mechanisms contributing to these gradients, in France, the United States, and the United Kingdom. MethodsAnalyses are based on harmonized data from large, nationally-representative samples from France, UK and US. We use regression models and decomposition methods to explore the relative role of several possible mechanisms in producing birthweight inequalities. ResultsInequalities in low birth weight across maternal education groups were relatively similar in the United States, the United Kingdom and France. However, the individual-level mechanisms producing such inequalities varied substantially across the three countries, with income being most important in the US, pregnancy smoking being most evident in France, and the UK occupying an intermediate position. Differences in the mechanisms producing birth health inequalities mirror differences in the policy environment in the three countries. ConclusionWhile inequalities in health appear from the earliest moments in many countries, our results suggest research on birth health inequalities, and therefore policies, is not easily generalizable across national contexts, and call for more scholarship in uncovering the “whys” of health inequalities in a variety of contexts.