Article
Mathematics
Xiao Wang, Xinmin Li
Summary: This paper investigates interval estimations for the mean of Pareto distribution with excess zeros, proposing three approaches based on fiducial generalized pivotal quantities (FGPQs). Simulation studies are conducted to evaluate the performance of the methods and compare them with other approaches, providing an analysis of their advantages and disadvantages. The methods are applied to a real phone call dataset for illustration.
Article
Mathematics, Applied
Emrah Altun, Hana Alqifari, Mohamed S. Eliwa
Summary: Count regression models are important for modeling discrete dependent variables with known covariates. This study introduces a new model, the zero-inflated Poisson generalized Lindley regression model, to replace the zero-inflated negative-binomial regression model. The Poisson generalized-Lindley distribution is re-parametrized and its parameter estimation problem is discussed using maximum likelihood estimation. The efficiency of parameter estimation of the proposed model is evaluated through simulation studies and the success of the model in handling zero inflation is tested using two datasets. The proposed model outperforms the negative-binomial regression model in cases of over-dispersion and zero inflation.
Article
Marine & Freshwater Biology
M. J. Lima, P. Relvas, A. B. Barbosa
Summary: This study aimed to evaluate the spatial-temporal variability patterns and phenology of key toxigenic phytoplankton species in southern Portugal and identify the environmental drivers and predictors. The study found several environmental factors that influence harmful algal blooms and made suggestions for improving prediction models.
Article
Statistics & Probability
Mohammed Alqawba, Norou Diawara
Summary: This paper proposes Markov zero-inflated count time series models based on joint distribution of consecutive observations, addressing zero-inflation and serial dependence. Various copula functions and distributions like ZIP, ZINB, and ZICMP are considered, with likelihood-based inference and asymptotic properties studied. Simulation examples and application to sandstorm counts show advantages over existing models in modeling zero-inflated count time series data.
JOURNAL OF APPLIED STATISTICS
(2021)
Article
Engineering, Multidisciplinary
Artur J. Lemonte
Summary: This paper introduces a multivariate family of distributions for multivariate count data with excess zeros, deriving various general properties of the distribution, with marginal distributions being univariate zero-inflated Bell distributions. Model parameters are estimated using traditional maximum likelihood estimation methods, with a simple EM algorithm developed to calculate the maximum likelihood estimates. Empirical applications using real multivariate count data demonstrate the usefulness of the new class of distributions and offer comparisons with other related distributions.
APPLIED MATHEMATICAL MODELLING
(2022)
Article
Geosciences, Multidisciplinary
Frank Badu Osei, Alfred Stein, Veronica Andreo
Summary: Spatial disease modeling is an important tool in public health, and the use of zero-inflated mixture spatially varying coefficient models shows promising results for analyzing cholera data. The ZINB model outperformed the ZIP model in terms of fit and estimation of zero counts. The spatially varying effects of precipitation and temperature on cholera were found to have both increasing and decreasing gradients, emphasizing the importance of considering spatial factors in disease monitoring.
SPATIAL STATISTICS
(2022)
Article
Statistics & Probability
Maher Kachour, Christophe Chesneau
Summary: This paper introduces a new distribution model, ZPMOIEP distribution, for count data that may have excess zeros and/or ones, and/or minus ones. The properties of the distribution are explored and the estimation of unknown parameters is investigated. Simulation experiments are conducted to evaluate the performance of the estimation. The applicability of the proposed distribution is examined using a dataset on football scores.
JOURNAL OF APPLIED STATISTICS
(2023)
Article
Chemistry, Multidisciplinary
Sangsung Park, Sunghae Jun
Summary: A large part of big data is made up of text documents, and analyzing this data requires preprocessing and building a structured document-word matrix. This matrix represents the frequency of words in each document and helps to improve predictive model performance. This paper proposes a method to solve the sparsity problem caused by the abundance of zero values in the matrix, and uses compound Poisson linear modeling. By comparing the Akaike information criterion (AIC) values of the proposed model with traditional models, the validity and effectiveness of the method are verified.
APPLIED SCIENCES-BASEL
(2023)
Article
Multidisciplinary Sciences
Razik Ridzuan Mohd Tajuddin, Noriszura Ismail, Kamarulzaman Ibrahim
Summary: This study introduces estimation methods for the OIPP distribution, including MLE, OLSE, MME, and RPE, which are all asymptotically unbiased and consistent. Additionally, a novel one-inflation index is proposed to assess the dataset for excess ones, determining that OLSE and MLE are the best estimators for the OIPP distribution.
JOURNAL OF TAIBAH UNIVERSITY FOR SCIENCE
(2021)
Article
Engineering, Multidisciplinary
Xin Lai, Xin Lian, Liu Liu, Jiayin Wang, Yuqian Liu, Ka Chun Chong
Summary: This paper presents a generalized likelihood ratio (GLR) based control chart for better monitoring the risk-adjusted ZIP process. The proposed method efficiently detects random shifts in both parameters and demonstrates superior performance in simulation studies and real-world datasets.
QUALITY AND RELIABILITY ENGINEERING INTERNATIONAL
(2023)
Article
Marine & Freshwater Biology
Kyla J. Kelly, Amjad Mansour, Chen Liang, Andrew M. Kim, Lily A. Mancini, Matthew J. Bertin, Bethany D. Jenkins, David A. Hutchins, Fei-Xue Fu
Summary: Toxic Pseudo-nitzschia blooms along the west coast of the United States are associated with seasonal upwelling and marine heatwaves. However, the mechanisms driving toxic bloom formation under these contrasting conditions remain poorly understood.
Article
Materials Science, Multidisciplinary
Fuxiang Liu, Jianing Liu, Peng Xu
Summary: This paper introduces a flexible statistical model for analyzing zero-inflated continuous data, which involves a novel zero-inflated Rayleigh (ZIR) distribution. The properties of this distribution, including moment, entropy, order statistics, are derived. Some interesting conclusions are drawn by discussing the interrelationships between various extropies. Parameters of the ZIR distribution are estimated by both moments estimation and maximum likelihood estimation, and the properties of these estimators are investigated.
RESULTS IN PHYSICS
(2023)
Article
Computer Science, Interdisciplinary Applications
Qiuyan Hu, Liu Liu
Summary: This study introduces an upper-sided exponentially weighted moving average control chart using a weighted score test statistic for detecting positive shifts in parameters of the Poisson part in zero-inflated Poisson models. The proposed method improves detection efficiency for unnatural heterogeneity variability and shows better performance than the existing PR-ZIP chart in detecting small to moderate shifts. Additionally, the simulation results via the Monte Carlo methodology and a practical example application demonstrate the utility of the proposed chart.
COMPUTERS & INDUSTRIAL ENGINEERING
(2021)
Article
Transportation Science & Technology
Ayca Altay, Melike Baykal-Gursoy
Summary: This study developed a zero-inflated Bayesian approach to model the rate of missed defects during imperfect inspections and studied optimizing track maintenance based on this model.
TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
(2022)
Article
Computer Science, Interdisciplinary Applications
M. Shirozhan, Hassan S. Bakouch, M. Mohammadpour
Summary: Time series modeling and forecasting of infectious diseases are crucial for understanding disease transmission behavior and developing better policies. A flexible INAR(1) time series model based on dependent zero-inflated count series is proposed, with a consideration of a flexible discrete distribution for innovation terms. The statistical properties and interpretation of the proposed model are provided, and the unknown parameters are estimated using various methods. The efficiency of the estimates is evaluated through Monte Carlo simulation, and recent contagious cases are analyzed using fitting and modeling techniques.
MATHEMATICS AND COMPUTERS IN SIMULATION
(2023)
Article
Multidisciplinary Sciences
Catarina Churro, Ana P. Semedo-Aguiar, Alexandra D. Silva, Jose B. Pereira-Leal, Ricardo B. Leite
SCIENTIFIC REPORTS
(2020)
Article
Marine & Freshwater Biology
Raquel A. F. Neves, Miguel A. Pardal, Silvia M. Nascimento, Alexandra Silva, Paulo J. Oliveira, Elsa T. Rodrigues
AQUATIC TOXICOLOGY
(2020)
Article
Oceanography
Mariana Santos, Helena Mourino, Maria Teresa Moita, Alexandra Silva, Ana Amorim, Paulo B. Oliveira
CONTINENTAL SHELF RESEARCH
(2020)
Article
Marine & Freshwater Biology
Eileen Bresnan, Fabiola Arevalo, Catherine Belin, Maria A. C. Branco, Allan D. Cembella, Dave Clarke, Jorge Correa, Keith Davidson, Monika Dhanji-Rapkova, Raul Fernandez Lozano, Margarita Fernandez-Tejedor, Hafsteinn Guofinnsson, David Jaen Carbonell, Aitor Laza-Martinez, Maud Lemoine, Adam M. Lewis, Luz Maman Menedez, Benjamin H. Maskrey, April McKinney, Yolanda Pazos, Marta Revilla, Raffaele Siano, Alexandra Silva, Sarah Swan, Andrew D. Turner, Laura Schweibold, Pieter Provoost, Henrik Enevoldsen
Summary: The study utilized the IOC-ICES-PICES Harmful Algal Event Database to examine the diversity and spatiotemporal distribution of harmful algal events along the Atlantic margin of Europe from 1987-2018, showcasing different toxin groups and regional differences.
Article
Environmental Sciences
Marcos Mateus, Miguel Remondes, Ligia Pinto, Alexandra Silva
FRONTIERS IN MARINE SCIENCE
(2021)
Article
Oceanography
Jorge Ramos, Miriam Tuaty-Guerra, Mariana Almeida, Ana C. Raposo, Maria J. Gaudencio, Alexandra D. Silva, Nuno Rodrigues, Sergio M. Leandro, Miguel Caetano
Summary: The Nazare acute accent artificial reef (NAR) off the western coast of Portugal aimed to improve social and economic resilience of local communities by creating a safer and closer area for fishing. The reef, developed using a multidisciplinary approach, was found to be mature and colonized by various macrobenthic assemblages without negative impacts on soft bottom macrofauna. It also contributed to fish aggregation, particularly attracting small fish species, thereby potentially benefitting the local fishing community.
OCEAN & COASTAL MANAGEMENT
(2021)
Article
Biology
Miriam Romagosa, Sergi Perez-Jorge, Irma Cascao, Helena Mourino, Patrick Lehodey, Andreia Pereira, Tiago A. Marques, Luis Matias, Monica A. Silva
Summary: The study examined the vocalizations of fin whales and found that the production of 20-Hz calls is influenced by season and year, supporting their reproductive function hypothesis, while the 40-Hz calls are associated with prey biomass, indicating a food-associated function. Understanding animal signals can aid in identifying functional habitats and predicting impacts of human activities on conservation.
PROCEEDINGS OF THE ROYAL SOCIETY B-BIOLOGICAL SCIENCES
(2021)
Article
Medicine, General & Internal
Tiago Dias Domingues, Anna D. Grabowska, Ji-Sook Lee, Jose Ameijeiras-Alonso, Francisco Westermeier, Carmen Scheibenbogen, Jacqueline M. Cliff, Luis Nacul, Eliana M. Lacerda, Helena Mourino, Nuno Sepulveda
Summary: The study investigated the association between ME/CFS and chronic herpesvirus infections, analyzing serological data from different subgroups of patients. While the data suggested a potential differentiation of patient subgroups based on herpesvirus serology, this finding may be limited by the issue of multiple testing.
FRONTIERS IN MEDICINE
(2021)
Review
Environmental Sciences
Jose A. Fernandes-Salvador, Keith Davidson, Marc Sourisseau, Marta Revilla, Wiebke Schmidt, Dave Clarke, Peter I. Miller, Paola Arce, Raul Fernandez, Luz Maman, Alexandra Silva, Callum Whyte, Maria Mateo, Patricia Neira, Marcos Mateus, Manuel Ruiz-Villarreal, Luis Ferrer, Joe Silke
Summary: The shellfish aquaculture industry in the European Atlantic Arc is impacted by harmful algal blooms that produce biotoxins accumulating in shellfish flesh, affecting consumer health. Regulatory monitoring focuses on harmful cells and toxin concentrations, but there is a need for early warning systems for business planning. Web portals and operational Early Warning Systems (EWS) are being developed, incorporating environmental data parameters and varied forecasting approaches to mitigate HAB-generated harmful effects. Advanced EWS include satellite data and oceanographic modeling to predict HAB behavior, with traffic light indices for easy risk assessment and expert interpretation of multiple data streams for future risk assessment. Proof-of-concept EWS combine model information with in-situ data, sometimes using machine learning-based approaches.
FRONTIERS IN MARINE SCIENCE
(2021)
Article
Ecology
P. Fonseca, A. D. Silva, M. M. Angelico, S. Garrido
Summary: This study investigated the diets of three abundant coastal pelagic fish species in the eastern Atlantic and estimated the impact of cannibalism and intraguild predation on egg mortality. The study found that there was diet overlap between the three species, but their diets varied. Sardine was found to have the greatest impact on fish egg mortality.
MARINE ECOLOGY PROGRESS SERIES
(2022)
Article
Engineering, Biomedical
Martim Almeida, Helena Mourino, Arnaldo G. Batista, Sara Russo, Filipa Esgalhado, Catarina R. Palma dos Reis, Fatima Serrano, Manuel Ortigueira
Summary: The study evaluates the dependency of selected EHG features on various factors using Linear Mixed Models. The results suggest a dependency of certain EHG features on BMI and placental position, showing a low-pass filtering effect. However, the variation of entropy features with gestational age was not statistically validated.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2022)
Article
Immunology
Diana Tavares, Helena Mourino, Cristina Anton Rodriguez, Carlos Martin Saborido
Summary: This study evaluates the cost effectiveness of switching from trivalent inactivated vaccine (TIV) to quadrivalent inactivated vaccine (QIV) in the Portuguese elderly population from the perspective of the National Health Service. The findings indicate that QIV is not cost effective due to its high cost.
Article
Chemistry, Analytical
Daniela Martins, Arnaldo Batista, Helena Mourino, Sara Russo, Filipa Esgalhado, Catarina R. Palma dos Reis, Fatima Serrano, Manuel Ortigueira
Summary: The interference of MR-EMG in electrohysterogram poses challenges in utilizing Alv waves for monitoring tasks such as preterm birth prediction. This study presents an adaptive filter selection algorithm to reduce this interference and optimize parameters for better filtering performance.
Article
Oncology
Adalgisa Guerra, Filipe Caseiro Alves, Kris Maes, Steven Joniau, Joao Cassis, Rui Maio, Marilia Cravo, Helena Mourino
Summary: A predictive model based on MRI features, histological and clinical variables has been developed for the accurate prediction of pathology-detected extracapsular extension in prostate cancer patients. The model showed satisfactory performance in distinguishing pECE+ and pECE- patients.
Article
Multidisciplinary Sciences
Tiago Dias Domingues, Joao Malato, Anna D. Grabowska, Ji-Sook Lee, Jose Ameijeiras-Alonso, Przemyslaw Biecek, Luis Graca, Helena Mourin, Carmen Scheibenbogen, Francisco Westermeier, Luis Nacul, Jacqueline M. Cliff, Eliana Lacerda, Nuno Sepulveda
Summary: In this study, the researchers re-analyzed data from ME/CFS and MS patients and found that IgG antibody data is more informative in explaining the symptoms of MS patients than ME/CFS patients. However, the clinical implications of these findings in ME/CFS patients remain to be determined due to the fluctuating nature of their symptoms.