Article
Statistics & Probability
Paul A. Smith, Chiara Bocci, Nikos Tzavidis, Sabine Krieg, Marc J. E. Smeets
Summary: Small area estimation is rarely used in business statistics due to challenges posed by skewed and variable variables like turnover. This study investigates various small area estimation methods for estimating industry activity in the retail sector in the Netherlands using tax register data. Results show the effectiveness of M-quantile small area estimators in reducing mean squared error compared to direct estimators.
JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES C-APPLIED STATISTICS
(2021)
Article
Automation & Control Systems
Elisa Cabana, Rosa E. Lillo
Summary: A novel discriminant analysis method based on robust reweighted shrinkage estimators and a threshold determined by robust Mahalanobis distance with adjusted quantile is proposed. Both simulation studies and real dataset examples demonstrate the effectiveness and computational efficiency of the proposed method.
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS
(2022)
Article
Computer Science, Information Systems
Erol Egrioglu, Eren Bas
Summary: The fuzzy regression functions approach is a non-rule-based and non-expert knowledge-based fuzzy inference system. It is based on regression analysis using the ordinary least squares method and fuzzy clustering method. However, the ordinary least squares method is not effective when there are outliers in the data set, which affects the fuzzy regression functions approach. Hence, robust intuitionistic fuzzy regression function approaches are proposed to handle outliers in the data set, and successful forecasting results are achieved on Bitcoin and gold time series.
INFORMATION SCIENCES
(2023)
Article
Economics
Christopher Oconnor
Summary: Standard methodologies used to identify vulnerable households rely on distributional assumptions that may lead to classification errors. This paper demonstrates that quantile models can improve this identification by relaxing these assumptions. Quantile models are robust and easy to implement, making them suitable for policymakers. Applying this strategy to data from Uganda shows that it more accurately identifies the future poor compared to standard approaches. The study highlights the benefits of relaxing distributional assumptions when identifying vulnerable populations.
ECONOMIC MODELLING
(2023)
Article
Economics
Daniel VandenHeuvel, Jinran Wu, You-Gan Wang
Summary: Standard methods for forecasting electricity loads lack robustness against cyberattacks, which can lead to severe consequences. This paper investigates a robust approach with data-driven tuning parameters, specifically an adaptive trimmed regression method that can better detect outliers and improve forecasts.
INTERNATIONAL JOURNAL OF FORECASTING
(2023)
Article
Economics
Li Qu
Summary: This study demonstrates that robust regression MM-estimation improves earnings forecast accuracy compared to OLS regression, especially for models with more variables. The impact of outliers on OLS regression increases with the number of variables.
INTERNATIONAL JOURNAL OF FORECASTING
(2021)
Article
Engineering, Mechanical
Qingrong Zou, Jianxi Zhao, Jici Wen
Summary: In this paper, a quantile regression framework is proposed for modeling fatigue curves, which eliminates the problem of distribution assumption and exhibits robustness in handling non-constant scale issues.
INTERNATIONAL JOURNAL OF FATIGUE
(2023)
Article
Mathematics, Applied
Gajendra K. Vishwakarma, Chinmoy Paul, Ali S. Hadi, A. M. Elsawah
Summary: Clustering analysis is widely used in various applications, such as marketing, biology, medical science, finance, data mining, image processing, data analysis and pattern recognition. The k-means, Hierarchical and self-organizing (Kohonen) map are widely used clustering algorithms. However, these clustering algorithms have some significant limitations and drawbacks.
JOURNAL OF COMPUTATIONAL AND APPLIED MATHEMATICS
(2023)
Article
Automation & Control Systems
Krzysztof Siminski
Summary: The paper analyzes neuro-fuzzy systems robust to outliers in classification and regression tasks, using a clustering algorithm to remove objects with low typicalities. Experiments demonstrate the efficacy of the modified neuro-fuzzy system to identify fuzzy models robust to high ratios of outliers.
INTERNATIONAL JOURNAL OF APPLIED MATHEMATICS AND COMPUTER SCIENCE
(2021)
Article
Computer Science, Interdisciplinary Applications
Julien Miron, Benjamin Poilane, Eva Cantoni
Summary: In the context of polytomous regression, the impact of outlying covariates on estimation and testing is shown to be more significant than misclassification alone. Two new estimators, along with corresponding tests, are introduced to address this problem and compared to existing alternatives.
COMPUTATIONAL STATISTICS & DATA ANALYSIS
(2022)
Article
Economics
Lukas Fryd, Ondrej Sokol
Summary: Subsidies for agriculture in the European Union have long been a debated issue, and research shows that they have a negative impact on farm efficiency, with the effect varying depending on the technical efficiency of the farm.
SOCIO-ECONOMIC PLANNING SCIENCES
(2021)
Article
Mathematics, Applied
Xi Chen, Weidong Liu, Xiaojun Mao
Summary: This paper investigates the reduced rank regression problem with heavy-tailed noises, using the quantile loss function and trace-norm regularized least-square problem. A distributed algorithm is developed, with theoretical guarantees for convergence rate and rank recovery established. Simulation analysis demonstrates the effectiveness of the method.
SCIENCE CHINA-MATHEMATICS
(2022)
Article
Psychology, Applied
S. Trevis Certo, Kristen Raney, Latifa Albader, John R. Busenbark
Summary: Organizational researchers have found problems with nonnormal dependent variable distributions, particularly those that include negative values. In two studies, the authors examine the nonnormality of firm performance measures and the implications it has on statistical analyses. They find extreme levels of skewness and kurtosis in these measures and reveal that common transformations used to address nonnormality are ineffective. They also show that extreme nonnormality reduces efficiency and increases Type II errors in statistical approaches.
ORGANIZATIONAL RESEARCH METHODS
(2023)
Article
Automation & Control Systems
Fouzi Douak, Noureddine Ghoggali, Rachid Hedjam, Mohamed Lamine Mekhalfi, Nabil Benoudjit, Farid Melgani
Summary: This work introduces a new algorithm that combines nonlinear kernel regressors with optimization based on a multi-objective genetic algorithm to improve techniques used in spectroscopic data regression analysis. The algorithm simultaneously optimizes multiple complementary objectives for better outlier detection.
JOURNAL OF CHEMOMETRICS
(2021)
Article
Economics
Young C. Joo, Sung Y. Park
Summary: Oil price volatility has asymmetric effects on stock returns, which vary depending on both stock returns levels and oil market conditions.
Article
Health Care Sciences & Services
Marco Geraci, Nansi S. Boghossian, Alessio Farcomeni, Jeffrey D. Horbar
STATISTICAL METHODS IN MEDICAL RESEARCH
(2020)
Article
Mathematical & Computational Biology
Alessio Farcomeni, Marco Geraci
STATISTICS IN MEDICINE
(2020)
Review
Nutrition & Dietetics
Michael W. Beets, R. Glenn Weaver, John P. A. Ioannidis, Marco Geraci, Keith Brazendale, Lindsay Decker, Anthony D. Okely, David Lubans, Esther van Sluijs, Russell Jago, Gabrielle Turner-McGrievy, James Thrasher, Xiaming Li, Andrew J. Milat
INTERNATIONAL JOURNAL OF BEHAVIORAL NUTRITION AND PHYSICAL ACTIVITY
(2020)
Article
Health Care Sciences & Services
Marco Geraci, Alessio Farcomeni
STATISTICAL METHODS IN MEDICAL RESEARCH
(2020)
Article
Health Care Sciences & Services
Carlene A. Mayfield, Marco Geraci, Michael Dulin, Jan M. Eberth, Anwar T. Merchant
Summary: This study analyzed the social and demographic characteristics of heavy users of the emergency department, finding that the frequency and charges of ED visits were associated with patient insurance coverage, number of outpatient visits, and demographic characteristics.
JOURNAL OF EVALUATION IN CLINICAL PRACTICE
(2021)
Letter
Gastroenterology & Hepatology
Dario Sorrentino, Marco Geraci, Anna Kuballa
CLINICAL GASTROENTEROLOGY AND HEPATOLOGY
(2021)
Article
Endocrinology & Metabolism
Ethan T. Hunt, Lauren von Klinggraeff, Alexis Jones, Sarah Burkart, Rodrick Dugger, Bridget Armstrong, Michael W. Beets, Gabrielle Turner-McGrievy, Marco Geraci, R. Glenn Weaver
Summary: The study found that compared to White and FRPL eligible children, Black and non-eligible children had a lower proportion of days meeting obesity behavior guidelines during school. Significant differences were observed in the changes of meeting activity and sleep guidelines from school to summer between Black and White children. Differences in activity changes were also observed between children eligible and ineligible for FRPL.
OBESITY SCIENCE & PRACTICE
(2021)
Article
Statistics & Probability
Alessio Farcomeni, Marco Geraci, Cinzia Viroli
Summary: Classifiers based on directional quantiles are introduced, and theoretical results are derived for selecting optimal quantile levels given a direction and vice versa. It is also shown that the proposed classifier has a probability of correct classification converging to one, under the conditions that population distributions differ by at most a location shift and the number of directions diverges at the same rate as the problem's dimension. The performance of the proposed classifiers is demonstrated through simulation studies and a real data example.
JOURNAL OF COMPUTATIONAL AND GRAPHICAL STATISTICS
(2022)
Article
Obstetrics & Gynecology
Nansi S. Boghossian, Marco Geraci, Erika M. Edwards, Jeffrey D. Horbar
Summary: Quality of care in Black and Hispanic serving (BHS) as well as not BHS (NBHS) neonatal intensive care units improved similarly over time in most regions, with focus needed on variations within and between divisions.
JOURNAL OF PERINATOLOGY
(2022)
Article
Mathematical & Computational Biology
Carmen D. Tekwe, Mengli Zhang, Raymond J. Carroll, Yuanyuan Luan, Lan Xue, Roger S. Zoh, Stephen J. Carter, David B. Allison, Marco Geraci
Summary: Quantile regression is a useful method for modeling associations between variables, especially when the relationships between covariates and the outcome distribution are complex. However, regression quantiles may be biased in the presence of measurement error in the covariates. This study proposes a two-stage strategy to consistently fit linear quantile regression models with function-valued covariates that may be measured with error, and evaluates the robustness of the measurement error correction using simulation studies and empirical application.
Article
Health Care Sciences & Services
Marco Geraci, Alessio Farcomeni
Summary: This study develops quantile regression methods for discrete responses by extending Parzen's definition. The proposed methods use interpolation and the inverse of the conditional mid-distribution function to estimate regression coefficients. Simulation results show that the proposed methods perform well for discrete responses.
STATISTICAL METHODS IN MEDICAL RESEARCH
(2022)
Article
Mathematical & Computational Biology
Marco Geraci
Summary: Accelerometers are commonly used in human medical and public health research to measure physical movement. The accelerometer output provides intensity and timing information, which can be used to define activity bouts. In some cases, considering both dimensions can provide a broader understanding of the phenomenon under study.
STATISTICS IN MEDICINE
(2023)
Article
Health Care Sciences & Services
Nicole Rossi, Luca Golinelli, Federica Bersani, Marco Geraci
Summary: This study investigated factors associated with non-conformities (NCs) in surgical safety checklists and explored the potential impact of the COVID-19 crisis. The overall compliance with the checklists was satisfactory, but there is room for improvement as around 7% of surgeries had NCs. Factors such as incomplete checklists, urgent surgeries, and the pandemic were associated with an increased risk of NCs. The findings highlight the importance of continuous improvement and adapting checklist practices during exceptional circumstances.
JOURNAL OF EVALUATION IN CLINICAL PRACTICE
(2023)
Article
Public, Environmental & Occupational Health
Lauren A. Reid, Marco Geraci, Jason A. Mendoza, Anwar T. Merchant, Beth A. Reboussin, Russell R. Pate, Lawrence M. Dolan, Katherine A. Sauder, Eva Lustigova, Grace Kim, Angela D. Liese
Summary: This study examined the association between household food insecurity (HFI) and physical activity (PA) in youth and young adults (YYA) with type 1 and type 2 diabetes. The results showed that YYA with type 1 diabetes who experienced HFI spent more time walking, while YYA with type 2 diabetes who experienced HFI spent more time sitting. The study suggests further research on the relationship between HFI and different domains of walking, such as leisure walking, and the use of objective PA measures to corroborate the findings.
JOURNAL OF PHYSICAL ACTIVITY & HEALTH
(2023)
Meeting Abstract
Sport Sciences
Lauren A. Reid, Marco Geraci, Jason A. Mendoza, Beth A. Reboussin, Russell R. Pate, Katherine A. Sauder, Lawrence M. Dolan, Grace Kim, Jean M. Lawrence, Angela D. Liese
MEDICINE & SCIENCE IN SPORTS & EXERCISE
(2020)