Article
Ecology
Soumen Dey, Richard Bischof, Pierre P. A. Dupont, Cyril Milleret
Summary: Spatial capture-recapture (SCR) analysis is commonly used in wildlife management and conservation decisions. This study investigates the effects of misspecifications in the detection function of SCR models on abundance and home range size estimates. The results show that abundance estimates are robust, but home range size estimates are sensitive to misspecifications. The study also suggests the use of Bayesian p-values to detect misspecifications. The choice of detection function can have substantial consequences on inferences about space use. Therefore, additional goodness-of-fit diagnostics are needed for Bayesian SCR models to identify a wider range of misspecifications.
ECOLOGY AND EVOLUTION
(2022)
Article
Automation & Control Systems
Krishnakumar Balasubramanian, Tong Li, Ming Yuan
Summary: The study examines the statistical performance of reproducing kernel Hilbert space (RKHS) embedding in testing problems, showing that a basic version of kernel embedding test may not be optimal, especially when chi(2) distance is used as the separation metric. The authors propose a simple modification to address this issue, demonstrating that the moderated approach offers optimal tests for various deviations from null hypotheses and can adapt over multiple interpolation spaces. Numerical experiments support the effectiveness of the approach.
JOURNAL OF MACHINE LEARNING RESEARCH
(2021)
Article
Computer Science, Information Systems
Alexander Shapiro, Yao Xie, Rui Zhang
Summary: The research develops a general theory for the goodness-of-fit test to non-linear models, where the residual of the model fit follows a chi(2) distribution related to the model order and problem dimension. A sequential method for selecting model orders is presented, demonstrating broad applications in machine learning and signal processing.
IEEE TRANSACTIONS ON INFORMATION THEORY
(2021)
Article
Statistics & Probability
Rizky Reza Fauzia, Yoshihiko Maesono
Summary: This article proposes kernel-type smoothed Kolmogorov-Smirnov and Cramer-von Mises tests for data on general interval using bijective transformations, aiming to solve the boundary problem. Numerical studies are conducted to illustrate the performance of the estimator and the tests.
COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION
(2023)
Article
Mathematics
A. Pekgor
Summary: Recently, new goodness-of-fit tests based on Kullback-Leibler divergence and likelihood ratio have been introduced for the Cauchy distribution, claiming to be more powerful than traditional tests. This study proposes a novel test for the Cauchy distribution and derives its asymptotic null distribution. Critical values are determined through Monte Carlo simulation for various sample sizes, and power analysis reveals the superiority of the proposed test under certain conditions.
JOURNAL OF MATHEMATICS
(2023)
Article
Computer Science, Interdisciplinary Applications
Sangyeol Lee, Byungtae Seo
Summary: This study examines a goodness of fit test based on quadratic distance (QD) in composite hypotheses, focusing on a smoothing kernel-based QD test and its bootstrap version. Through Monte Carlo simulations, the performance of these tests is compared with others, demonstrating the validity of the proposed method.
JOURNAL OF STATISTICAL COMPUTATION AND SIMULATION
(2021)
Article
Statistics & Probability
Dimitrios Bagkavos, Prakash N. Patil, Andrew T. A. Wood
Summary: This article introduces a novel goodness-of-fit test for a continuous parametric model in the multivariate setting. The test is based on aggregating local discrepancies between a nonparametric estimate of the density and the parametrically estimated density under the null model. The article presents theoretical results, including the asymptotic distribution of the test statistic and its power under fixed and local alternatives, and also introduces a bandwidth selector and a bootstrap size function approximation.
JOURNAL OF MULTIVARIATE ANALYSIS
(2023)
Article
Biochemical Research Methods
Mengqi Zhang, Sahar Gelfman, Cristiane Araujo Martins Moreno, Janice M. McCarthy, Matthew B. Harms, David B. Goldstein, Andrew S. Allen
Summary: Gene set-based signal detection analysis is used to detect the association between a trait and a set of genes by accumulating signals across the genes in the set. This study presents a flexible framework based on tail-focused GOF statistics, which depends on two critical parameters. Guidance on statistic selection is provided and the methods are implemented in the user-friendly R package wHC. The methods are applied to a study on amyotrophic lateral sclerosis.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Statistics & Probability
Jiawei Zhang, Jie Ding, Yuhong Yang
Summary: The article proposes a methodology called BAGofT for assessing the goodness of fit of a general classification procedure. The method splits the data into a training set and a validation set, and identifies the most severe regions of underfitting by adaptingively grouping the training set. A test statistic is then calculated based on this grouping and a comparison between the estimated success probabilities and the actual observed responses from the validation set. The BAGofT has a broader scope than existing methods in testing parametric classification models.
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
(2023)
Article
Computer Science, Interdisciplinary Applications
Chihiro Watanabe, Taiji Suzuki
Summary: This study developed a new goodness-of-fit test for latent block models to test whether an observed data matrix fits a given set of row and column cluster numbers, or it consists of more clusters in at least one direction of the row and the column.
COMPUTATIONAL STATISTICS & DATA ANALYSIS
(2021)
Article
Statistics & Probability
Adrian Baddeley, Tilman M. Davies, Suman Rakshit, Gopalan Nair, Greg McSwiggan
Summary: This paper develops a practical statistical methodology combining traditional kernel methods with diffusion smoothing for estimating the density of two-dimensional spatial point pattern data. Diffusion smoothing exhibits better adaptive performance and robustness compared to traditional Gaussian kernel smoothing, and it can be applied in various fields such as archaeology and epidemiology.
STATISTICAL SCIENCE
(2022)
Article
Automation & Control Systems
Changming Cheng, Er-Wei Bai
Summary: In order to achieve a parsimonious model, it is important to rank input variables based on goodness of fit in nonlinear and nonparametric system identification. By establishing numerical algorithms in a reproducing kernel Hilbert space, it is possible to address the nonparametric nature of the unknown system and unknown distribution conditions successfully.
IEEE TRANSACTIONS ON AUTOMATIC CONTROL
(2021)
Article
Mathematical & Computational Biology
Martin L. Hazelton
Summary: The spatial relative risk function describes differences in the geographical distribution of two types of points in epidemiological studies. Estimation of this function is challenging due to the spatial inhomogeneity in the distributions. We propose a new lasso-type estimator that shrinks a standard kernel estimator towards zero. The performance of the lasso estimator is encouraging in simulation studies and real-world examples.
STATISTICS IN MEDICINE
(2023)
Letter
Business, Finance
Valentin Patilea, Hamdi Raissi
Summary: This study investigates the higher order dynamics of individual stocks and finds that classical powers correlation analysis may lead to erroneous assessment of volatility persistence when the zero return probability varies over time. To address this issue, new diagnostic tools are proposed that are robust to changes in the zero return probability. Additionally, robust powers correlation analysis is developed to account for time-varying zero return probability and non-constant unconditional variance. The study also demonstrates that the use of classical powers correlations may lead to doubtful conclusions, while the proposed diagnostic tools offer a rigorous analysis of short-run volatility effects.
JOURNAL OF FINANCIAL ECONOMETRICS
(2023)
Article
Computer Science, Interdisciplinary Applications
Feifei Chen, M. Dolores Jimenez-Gamero, Simos Meintanis, Lixing Zhu
Summary: A general and relatively simple method for constructing multivariate goodness-of-fit tests is presented in this paper, with a focus on elliptical distributions. The method is based on characterizing probability distributions through their characteristic function. The consistency and other limit properties of the new test statistics are investigated. Additionally, a simulation study is conducted to compare the proposed tests with previous and more recent competitors.
COMPUTATIONAL STATISTICS & DATA ANALYSIS
(2022)
Article
Statistics & Probability
Lina Liao, Cheolwoo Park, Hosik Choi
ANNALS OF THE INSTITUTE OF STATISTICAL MATHEMATICS
(2019)
Article
Neurosciences
Li-Yu Wang, Jongik Chung, Cheolwoo Park, Hosik Choi, Amanda L. Rodrigue, Jordan E. Pierce, Brett A. Clementz, Jennifer E. McDowell
HUMAN BRAIN MAPPING
(2019)
Article
Biology
Cheolwoo Park, Hosik Choi, Chris Delcher, Yanning Wang, Young Joo Yoon
Article
Computer Science, Interdisciplinary Applications
Hosik Choi, J. C. Poythress, Cheolwoo Park, Jong-June Jeon, Changyi Park
JOURNAL OF STATISTICAL COMPUTATION AND SIMULATION
(2019)
Article
Statistics & Probability
Sungtaek Son, Cheolwoo Park, Yongho Jeon
JOURNAL OF APPLIED STATISTICS
(2020)
Article
Green & Sustainable Science & Technology
Subash Dahal, Dorcas Franklin, Anish Subedi, Miguel Cabrera, Dennis Hancock, Kishan Mahmud, Laura Ney, Cheolwoo Park, Deepak Mishra
Article
Computer Science, Interdisciplinary Applications
Jib Huh, Derek Dyal, Cheolwoo Park
Summary: In this paper, a scale-space statistical tool called the significant zero crossings of derivatives (SiZer) is developed for single-index models (SIMs), successfully capturing trends in simulation and real applications.
JOURNAL OF STATISTICAL COMPUTATION AND SIMULATION
(2021)
Article
Statistics & Probability
Ilsuk Kang, Cheolwoo Park, Young Joo Yoon, Changyi Park, Soon-Sun Kwon, Hosik Choi
Summary: This paper focuses on the classification problems when histograms are used as or aggregated into predictors. Conventional classification methods convert histograms into vector-valued data using summary values, which neglect the distributional information in histograms. To address this issue, the authors propose a margin-based classifier named support histogram machine (SHM) utilizing the support vector machine framework and the Wasserstein-Kantorovich metric. The experimental results demonstrate the superior performance of SHM compared to summary-value-based methods.
JOURNAL OF APPLIED STATISTICS
(2023)
Article
Statistics & Probability
J. C. Poythress, Cheolwoo Park, Jeongyoun Ahn
Summary: A proposed method aims to characterize the dominant modes of co-variation between variables in two datasets while performing variable selection accurately. The method relies on a sparse, low rank approximation of a matrix containing pairwise association measures between variables from the two sets, closely related to sparse canonical correlation analysis methods. Through simulations, it is shown that the proposed method outperforms state-of-the-art sparse CCA algorithms in terms of variable selection accuracies.
JOURNAL OF APPLIED STATISTICS
(2022)
Article
Statistics & Probability
J. C. Poythress, Jeongyoun Ahn, Cheolwoo Park
Summary: This paper introduces a method for fitting a generalized linear model with a three-dimensional image covariate using low-rank assumption and tensor singular value penalty. By developing corresponding algorithms, experimental results demonstrate that this method outperforms existing methods in simulation and real fMRI data decoding.
JOURNAL OF COMPUTATIONAL AND GRAPHICAL STATISTICS
(2022)
Article
Biochemical Research Methods
Jongik Chung, Brooke S. Jackson, Jennifer E. Mcdowell, Cheolwoo Park
Summary: The proposed method involves joint estimation of multiple precision matrices with regularized aggregation, which showed robustness and sensitivity in assessing cognitive control tasks using fMRI data. It outperformed traditional methods by capturing more robust associations between neural regions of interest and identifying practice-induced changes in neural efficiency.
JOURNAL OF NEUROSCIENCE METHODS
(2021)
Article
Statistics & Probability
Qihu Zhang, Cheolwoo Park, Jongik Chung
Summary: This paper focuses on the minimax estimation of covariance and precision matrices for high-dimensional time series with long-memory property. The authors generalize and extend the results for the convergence rates of covariance matrix estimation in various directions under a mild assumption, which was previously mentioned as an open problem in existing literature. Additionally, the minimax results for the convergence rates of precision matrix estimation under different norms are obtained, which were not considered in previous studies.
STATISTICS & PROBABILITY LETTERS
(2021)
Article
Computer Science, Interdisciplinary Applications
Arunava Samaddar, Brooke S. Jackson, Christopher J. Helms, Nicole A. Lazar, Jennifer E. McDowell, Cheolwoo Park
Summary: This study analyzed brain activation changes across different sessions and groups in a cognitive control task using a semi-parametric approach. The results show that utilizing shape invariance model can effectively quantify and test differences, providing a new pathway for studying the neural mechanisms of cognitive control tasks.
COMPUTATIONAL STATISTICS & DATA ANALYSIS
(2022)
Article
Computer Science, Theory & Methods
Ilsuk Kang, Hosik Choi, Young Joo Yoon, Junyoung Park, Soon-Sun Kwon, Cheolwoo Park
Summary: Multi-dimensional functional data analysis is an important research topic in medical research. Two clustering methods using the Frechet distance for multi-dimensional functional data are proposed. The methods extend an existing approach and enforce sparsity on functional variables. They demonstrate effectiveness through simulation examples and are applied to thyroid cancer data in South Korea.
STATISTICS AND COMPUTING
(2023)
Article
Cell Biology
Erin E. Kaiser, J. C. Poythress, Kelly M. Scheulin, Brian J. Jurgielewicz, Nicole A. Lazar, Cheolwoo Park, Steven L. Stice, Jeongyoun Ahn, Franklin D. West
Summary: This study investigated the prognostic value of commonly utilized MRI parameters in predicting functional outcomes in a porcine model of ischemic stroke. Specific MRI outputs and functional recovery variables were found to exhibit strong conditional dependencies, with a prognostic relationship identified between lesion volume and white matter integrity, and novel object exploration and gait performance. These results suggest the potential for predicting patient recovery using MRI analyses at chronic time points, given the anatomical similarities between pigs and humans that are critical in ischemic stroke pathophysiology.
NEURAL REGENERATION RESEARCH
(2021)
