Article
Ecology
Erin B. Lowe, Ben Iuliano, Claudio Gratton, Anthony R. Ives
Summary: This study introduces a new R package called 'scalescape' that estimates the spatial scale of landscape effects on biotic or abiotic responses. The package integrates well-used regression functions with landscape weighting methods, and provides a user guide and simulation experiments.
Article
Statistics & Probability
Ming-Yueh Huang, Shu Yang
Summary: This study proposes a method for robust inference of the conditional average treatment effect (CATE) of personalized treatment using observational data. The method reduces dimensionality twice to address the curse of dimensionality while maintaining nonparametric advantages and achieving different goals. Simulation and application results demonstrate that the proposed method outperforms existing competitors.
Article
Statistics & Probability
Xiaoyu Zhang, Mixia Wu, Colin O. Wu
Summary: The rank-tracking probability (RTP) is a useful statistical index for measuring the tracking ability of longitudinal disease risk factors in biomedical studies. This study proposes dynamic estimation methods based on semiparametric copula modeling and smoothing method, and compares the estimators under three smoothing ways. The results show that the C-RS estimator performs the best under the selected copula model and has smaller mean squared errors compared to unstructured smoothing methods.
Article
Statistics & Probability
Chunyu Wang, Maozai Tian, Man-Lai Tang
Summary: In this paper, we propose augmented inverse probability weighted (AIPW) local estimating equations to deal with missing data in nonparametric quantile regression. We adopt a nonparametric approach to estimate the propensity score and conditional expectations of estimating functions to avoid misspecification issues. The asymptotic properties of our proposed estimator are studied and the nonsmoothness problem of the check function is addressed using the majorisation-minimisation algorithm.
JOURNAL OF NONPARAMETRIC STATISTICS
(2022)
Article
Computer Science, Artificial Intelligence
Atanu Bhattacharjee, Gajendra K. Vishwakarma, Bhrigu K. Rajbongshi, Abhipsa Tripathy
Summary: This article introduces the features and applications of the MIIPW R package, which can be used to address missing values in longitudinal cohort data. It also provides a practical guide for solving missing data issues.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Mathematics
Fei Wang, Yuhao Deng
Summary: The augmented inverse probability weighting is a robust method for handling missing data and causal inference. It has the property of double robustness, ensuring consistency when either the propensity score model or the outcome regression model is specified correctly. Additionally, it can achieve first-order equivalence to the oracle estimator, even if the fitted models do not converge at the parametric root-n rate. We explore the non-asymptotic properties of this estimator for inferring population mean with missingness at random, as well as inferences for mean outcomes in observed and unobserved groups.
Article
Physics, Mathematical
Cyril Letrouit
Summary: In this work, we prove that the singularities of subelliptic wave equations only propagate along specific curves known as null-bicharacteristics and abnormal extremals, which are widely used in optimal control theory. Based on this result, we characterize the singular support of subelliptic wave kernels outside the diagonal and demonstrate the importance of abnormal extremals in the classical-quantum correspondence between sub-Riemannian geometry and sub-Laplacians.
COMMUNICATIONS IN MATHEMATICAL PHYSICS
(2022)
Article
Mathematics, Applied
Jin Jin, Peng Ye, Liuquan Sun
Summary: In this article, a class of weighted estimating equations is proposed for handling missing covariate data in biomedical studies. The approach effectively addresses the estimation of selection probabilities in both parametric and non-parametric modeling schemes.
SCIENCE CHINA-MATHEMATICS
(2022)
Article
Mathematical & Computational Biology
Di Shu, Peisong Han, Rui Wang, Sengwee Toh
Summary: The inverse probability weighted Cox model is used to estimate the marginal hazard ratio, requiring correct specification of the propensity score model. To address misspecification, a weighted estimation method rooted in empirical likelihood theory is proposed. The method demonstrates satisfactory performance in terms of consistency and efficiency in simulation studies and application to comparing postoperative hospitalization risks between two surgical procedures. Extending the method to multisite studies allows for site-specific propensity score models.
STATISTICS IN MEDICINE
(2021)
Article
Mathematical & Computational Biology
Peter Z. Schochet
Summary: In clustered randomized controlled trials, sample recruitment occurring after cluster randomization can lead to recruitment bias. This article presents a potential outcomes framework that yields a causal estimand related to individuals always recruited into the research conditions. A consistent inverse probability weighting estimator is developed using data on recruits only, and a generalized estimating equations approach is used to obtain robust clustered standard error estimators that account for estimation error in the weighting. A simple data collection strategy is discussed to improve the predictive accuracy of the logit propensity score models.
STATISTICS IN MEDICINE
(2023)
Article
Materials Science, Multidisciplinary
Jiaxin Zhang, Sirui Bi, Guannan Zhang
Summary: The study introduces a new nonlocal gradient method DGS for optimizing highly multi-modal loss functions. However, the method is currently limited to unconstrained optimization problems, while this research extends the method to constrained inverse design frameworks to achieve better design outcomes.
MATERIALS & DESIGN
(2021)
Article
Engineering, Civil
Marcos A. Valdebenito, Xiukai Yuan, Matthias G. R. Faes
Summary: This paper presents an approach for estimating the fuzzy failure probability associated with reliability problems. The main contribution of this work is addressing the problem with the First-Order Reliability Method, with some minor modifications. The proposed approach can provide an estimate of the membership function associated with the failure probability with reduced numerical costs.
Article
Computer Science, Information Systems
Tuan D. Pham
Summary: This paper introduces a method that integrates anisotropic averaging with the Laplacian kernels for grayscale image sharpening. Experimental results suggest certain advantages of the proposed linear convolution model for image sharpening over other existing methods, in terms of the balance of sharpness and natural visualization. One advantage of the proposed method is that it does not require any input statistical parameters.
Article
Statistics & Probability
Lan Wen, Miguel A. Hernan, James M. Robins
Summary: The study focuses on recently proposed multiply robust estimators of the longitudinal g-formula in the context of a survival outcome, comparing and validating these methods through simulation studies and practical applications.
SCANDINAVIAN JOURNAL OF STATISTICS
(2022)
Article
Multidisciplinary Sciences
Amal Helu
Summary: Since the formulation of entropy theory in 1940 and the discovery of the principle of maximum entropy in 1950, the application of entropy has expanded to various research areas, including hydrological and environmental sciences. The probability-weighted moments method has been recommended as an alternative to classical moments and is known for its robust parameter estimation. This article introduces the self-determined probability-weighted moments and compares it with other conventional methods using Monte Carlo simulations, providing a numerical example for the implementation.