Article
Computer Science, Interdisciplinary Applications
Zhiping Qiu, Jianwei Chen, Jin-Ting Zhang
Summary: This study proposes two global tests for comparing the mean vector functions of two multivariate functional samples, deriving their asymptotic random expressions and establishing their root-n consistencies. Simulation studies show that the proposed tests generally have higher or not worse powers compared to some existing competitors. A real data application illustrates the effectiveness of the proposed tests.
COMPUTATIONAL STATISTICS & DATA ANALYSIS
(2021)
Article
Statistics & Probability
Jun Li
Summary: In this paper, we propose asymptotic t-distributions for U-statistics that can accurately maintain Type I error rates for mean vector tests in high-dimensional data with small sample sizes. These tests are nonparametric and can be applied to normally distributed or heavy-tailed data. Simulation studies and an fMRI dataset application confirm the theoretical results and practical implementation of the proposed methods.
JOURNAL OF MULTIVARIATE ANALYSIS
(2023)
Article
Automation & Control Systems
Yu Liu, Degui Li, Yingcun Xia
Summary: This paper proposes an improvement to the MARS method by using linear combinations of covariates for dimension reduction. The proposed method achieves higher estimation efficiency by calculating gradients of the regression function using special basis functions of MARS and estimating the linear combinations through eigen-analysis. Numerical studies demonstrate the effectiveness of the proposed method in dimension reduction and regression estimation and prediction compared to traditional MARS and other nonparametric methods.
JOURNAL OF MACHINE LEARNING RESEARCH
(2023)
Article
Statistics & Probability
Caleb Kwon, Eric Mbakop
Summary: In this study, a novel estimator for the number of mixture components in a nonparametric finite mixture model is proposed. The estimator is based on the rank of an integral operator identified from the data and the stability of singular values under perturbations. It is shown to be consistent and has finite sample performance guarantees. Monte Carlo simulations demonstrate good performance for moderate sample sizes.
ANNALS OF STATISTICS
(2021)
Article
Statistics & Probability
Jingru Zhang, Hao Chen
Summary: This paper proposes extended graph-based test statistics to address the issue of repeated observations in graph-based tests. It also studies the asymptotic properties of these extended statistics and provides analytic formulae for approximating the p-values of the tests. The proposed tests are applied to analyze a phone-call network data set.
Article
Computer Science, Interdisciplinary Applications
Nan Lu, Lihong Wang
Summary: This paper investigates the estimation of mixing proportions and component density functions for a nonparametric multivariate mixture model that satisfies the condition of identifiability. A new estimation method is proposed that combines the advantages of the matrix simultaneous diagonalization method and the basis method. The consistency and convergence rate of the estimator are proved. Simulations and data analysis demonstrate the good performance and low computational cost of the proposed method for multivariate mixture models.
JOURNAL OF STATISTICAL COMPUTATION AND SIMULATION
(2022)
Article
Statistics & Probability
Linli Tang, Jun Li
Summary: Combining multiple tests has many real-world applications, but existing methods often overlook the underlying dependency among the tests. In this paper, a novel procedure based on data depth is proposed to address this issue. This method can incorporate the dependency among the tests automatically, and it is nonparametric and data-driven. The proposed method is demonstrated through the development of a new two-sample test for arbitrary data types that can be characterized by interpoint distances. Simulation studies and real data analysis show that the proposed test performs well in various settings and compares favorably with existing tests.
JOURNAL OF NONPARAMETRIC STATISTICS
(2022)
Article
Engineering, Electrical & Electronic
Sreeram C. Sreenivasan, Srikrishna Bhashyam
Summary: A nonparametric search problem was studied to detect L anomalous data streams, proposing universal distribution-free sequential tests and comparing their performance with fixed sample size tests through simulations.
IEEE SIGNAL PROCESSING LETTERS
(2021)
Article
Statistics & Probability
Linxi Liu, Yang Meng, Xiaoru Wu, Zhiliang Ying, Tian Zheng
Summary: Motivated by applications in high-dimensional settings, this paper proposes a novel approach for testing the equality of two or more populations by constructing a class of intensity centered score processes. The resulting tests are nonparametric, computationally simple, and applicable to high-dimensional data.
JOURNAL OF COMPUTATIONAL AND GRAPHICAL STATISTICS
(2022)
Article
Statistics & Probability
Daniel Baumgartner, John Kolassa
Summary: This paper examines the hypothesis that two samples come from the same population, using various alternative distributions and sample sizes to measure the power of each test. Recommendations are given for the more powerful test for each common distribution, based on whether the distribution has heavy or light tails.
COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION
(2023)
Article
Engineering, Mechanical
Kenny Santos, Nuno M. Silva, Joao P. Dias, Conceicao Amado
Summary: Motorcycle and motorized 2-3 wheelers accidents are of great concern for road safety, accounting for about 28% of overall fatalities worldwide. Speed plays a central role in the severity of injuries sustained in these accidents. Accident reconstruction is widely used in safety research to determine the main factors and causes of accidents. In this study, a methodology involving three different and complementary accident reconstruction methods was proposed and applied to a real accident involving a motorcycle and a passenger car. The results from the analyses conducted using PC-Crash and Ansys LS-DYNA showed good correlation with reality. The proposed methodology enables a more accurate estimation of motorcycle speeds, which is crucial for accident investigations.
ENGINEERING FAILURE ANALYSIS
(2023)
Article
Statistics & Probability
Jingru Zhang, Kathleen R. Merikangas, Hongzhe Li, Haochang Shou
Summary: Repeated observations are increasingly common in biomedical research and longitudinal studies. This paper proposes a novel graph-based two-sample test method for comparing object data with the same structure of repeated measures. Compared to traditional statistical methods, this method shows substantial power improvements and better control of type I errors.
ANNALS OF APPLIED STATISTICS
(2022)
Article
Statistics & Probability
Simone A. Padoan, Stefano Rizzelli
Summary: This paper focuses on a semiparametric Bayesian method for estimating max-stable distributions in arbitrary dimension. Consistency of the pertaining posterior distributions is established for fairly general, well-specified max-stable models, with margins that can be short-tailed, light-tailed, or heavy-tailed. The consistency results are also extended to the case where data are samples of block maxima that are only approximately max-stable, representing the most realistic inferential setting.
ANNALS OF STATISTICS
(2022)
Article
Statistics & Probability
Jin Wang
Summary: This article studies the finite-sample performance of the sample scale curve as an estimator of its population counterpart by simulation. It is found that the sample scale curve tends to underestimate its population counterpart and that the discrepancy increases quickly as dimension increases. The effect of kurtosis is minor compared with the effect of dimension.
COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION
(2023)
Article
Statistics & Probability
Hyunjae Lee, Byungtae Seo
Summary: Although the normal distribution is commonly used, it is not suitable for asymmetric or heavy tailed data. The skew-normal distribution is an important alternative, but it cannot approximate heavy tailed distributions well. In this paper, a semiparametric skew-normal distribution is proposed, which includes skew-normal distributions using a nonparametric scale mixture. The proposed model is applied to finite mixture models for more efficient and insightful model-based cluster analysis. A feasible algorithm is provided to compute all the parametric and nonparametric components in the model. Numerical examples are also presented to demonstrate the applicability of the proposed model.
COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION
(2023)
Article
Integrative & Complementary Medicine
Massimiliano Magro, Livio Corain, Silvia Ferro, Davide Baratella, Emanuela Bonaiuto, Milo Terzo, Vittorino Corraducci, Luigi Salmaso, Fabio Vianello
EVIDENCE-BASED COMPLEMENTARY AND ALTERNATIVE MEDICINE
(2016)
Article
Geography, Physical
F. Gabrieli, L. Lorain, L. Vettore
Article
Computer Science, Interdisciplinary Applications
Rosa Arboretti Giancristofaro, Stefano Bonnini, Livio Corain, Luigi Salmaso
JOURNAL OF STATISTICAL COMPUTATION AND SIMULATION
(2016)
Article
Endocrinology & Metabolism
Stefano Montelli, Matteo Suman, Livio Corain, Bruno Cozzi, Antonella Peruffo
NEUROENDOCRINOLOGY
(2017)
Article
Neurosciences
Jean-Marie Graic, Livio Corain, Antonella Peruffo, Bruno Cozzi, Dick F. Swaab
JOURNAL OF COMPARATIVE NEUROLOGY
(2018)
Article
Multidisciplinary Sciences
Cristina Ballarin, Michele Povinelli, Alberto Granato, Mattia Panin, Livio Corain, Antonella Peruffo, Bruno Cozzi
Article
Statistics & Probability
Rosa Arboretti, Riccardo Ceccato, Livio Corain, Fabrizio Ronchi, Luigi Salmaso
STATISTICAL PAPERS
(2018)
Article
Statistics & Probability
Livio Corain, Rosa Arboretti, Riccardo Ceccato, Fabrizio Ronchi, Luigi Salmaso
STATISTICAL MODELLING
(2019)
Article
Anatomy & Morphology
Antonella Peruffo, Livio Corain, Cristiano Bombardi, Cinzia Centelleghe, Enrico Grisan, Jean-Marie Graic, Pietro Bontempi, Annamaria Grandis, Bruno Cozzi
BRAIN STRUCTURE & FUNCTION
(2019)
Article
Anatomy & Morphology
L. Corain, E. Grisan, J. -M. Graic, R. Carvajal-Schiaffino, B. Cozzi, A. Peruffo
BRAIN STRUCTURE & FUNCTION
(2020)
Article
Anatomy & Morphology
Cristina Otero-Sabio, Cinzia Centelleghe, Livio Corain, Jean-Marie Graic, Bruno Cozzi, Miguel Rivero, Francesco Consoli, Antonella Peruffo
Summary: This study investigated the microscopic anatomy of the terminal portion of the airways of the lungs in five cetacean species, revealing structural differences among species and providing insights into the anatomy of the terminal airways crucial for prolonged breath-holding diving in cetaceans.
JOURNAL OF MORPHOLOGY
(2021)
Article
Anatomy & Morphology
Jean-Marie Graic, Antonella Peruffo, Livio Corain, Livio Finos, Enrico Grisan, Bruno Cozzi
Summary: By studying the primary visual cortex of Cetartiodactyls that live on land, in the sea, or in an amphibious environment, researchers have found significant differences in cortical structure compared to other mammals, with a close correlation between eye placement and cortical organization. Cetacean species, in particular, exhibit a distinct pattern of cortical organization compared to other mammals, possibly related to their deep-sea foraging habits, decreasing light availability, and reliance on echolocation.
BRAIN STRUCTURE & FUNCTION
(2022)
Proceedings Paper
Engineering, Biomedical
Enrico Grisan, Jean-Marie Graic, Livio Corain, Antonella Peruffo
2018 IEEE 15TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (ISBI 2018)
(2018)
Article
Anatomy & Morphology
Bruno Cozzi, Alberto De Giorgio, A. Peruffo, S. Montelli, M. Panin, C. Bombardi, A. Grandis, A. Pirone, P. Zambenedetti, L. Corain, Alberto Granato
BRAIN STRUCTURE & FUNCTION
(2017)
Correction
Anatomy & Morphology
Bruno Cozzi, Andrea De Giorgio, A. Peruffo, S. Montelli, M. Panin, C. Bombardi, A. Grandis, A. Pirone, P. Zambenedetti, L. Corain, Alberto Granato
BRAIN STRUCTURE & FUNCTION
(2017)