A5100363647- Statistical Methods and Inference
- Statistical Methods and Bayesian Inference
- Advanced Statistical Methods and Models
- Advanced Causal Inference Techniques
- Statistical Methods in Clinical Trials
- Bayesian Methods and Mixture Models
- Optimal Experimental Design Methods
- Numerical methods for differential equations
- Sparse and Compressive Sensing Techniques
- Statistical Distribution Estimation and Applications
- Electromagnetic Simulation and Numerical Methods
- Health Systems, Economic Evaluations, Quality of Life
- Algebraic Geometry and Number Theory
- Acute Myeloid Leukemia Research
- Control Systems and Identification
- Histone Deacetylase Inhibitors Research
- Advanced Numerical Methods in Computational Mathematics
- Advanced Statistical Process Monitoring
- Numerical methods in inverse problems
- Epigenetics and DNA Methylation
- Protein Degradation and Inhibitors
- Face and Expression Recognition
- Fault Detection and Control Systems
- PARP inhibition in cancer therapy
- Advanced Breast Cancer Therapies
China Medical University
2025
University of Miami
1999-2024
Tongji University
2023
Jiangxi Normal University
2012-2023
Shanghai Tongji Urban Planning and Design Institute
2023
University of Detroit Mercy
2023
Handan College
2023
Nankai University
2023
Capital Normal University
2022
University of Minnesota
2008-2020
Abstract Censored quantile regression offers a valuable supplement to Cox proportional hazards model for survival analysis. Existing work in the literature often requires stringent assumptions, such as unconditional independence of time and censoring variable or global linearity at all levels. Moreover, some uses recursive algorithms, making it challenging derive asymptotic normality. To overcome these drawbacks, we propose new locally weighted censored approach that adopts...
We introduce a quantile-adaptive framework for nonlinear variable screening with high-dimensional heterogeneous data. This has two distinctive features: (1) it allows the set of active variables to vary across quantiles, thus making more flexible accommodate heterogeneity; (2) is model-free and avoids difficult task specifying form statistical model in high dimensional space. Our independence procedure employs spline approximations marginal effects at quantile level interest. Under...
We consider the penalized generalized estimating equations (GEEs) for analyzing longitudinal data with high-dimensional covariates, which often arise in microarray experiments and large-scale health studies. Existing regression procedures assume independent rely on likelihood function. Construction of a feasible joint function is challenging, particularly correlated discrete outcome data. The GEE procedure only requires specifying first two marginal moments working correlation structure....
We investigate high-dimensional nonconvex penalized regression, where the number of covariates may grow at an exponential rate. Although recent asymptotic theory established that there exists a local minimum possessing oracle property under general conditions, it is still largely open problem how to identify estimator among potentially multiple minima. There are two main obstacles: (1) due presence minima, solution path nonunique and not guaranteed contain estimator; (2) even if known...
This work is concerned with testing the population mean vector of nonnormal high-dimensional multivariate data. Several tests for vector, based on modifying classical Hotelling T2 test, have been proposed in literature. Despite their usefulness, they tend to unsatisfactory power performance heavy-tailed data, which frequently arise genomics and quantitative finance. article proposes a novel nonparametric test general class distributions. With aid new tools modern probability theory, we...
The support vector machine (SVM) is a powerful binary classification tool with high accuracy and great flexibility. It has achieved success, but its performance can be seriously impaired if many redundant covariates are included. Some efforts have been devoted to studying variable selection for SVMs, asymptotic properties, such as consistency, largely unknown when the number of predictors diverges infinity. In this work, we establish unified theory general class nonconvex penalized SVMs. We...
Salicylate and acetylsalicylic acid are potent widely used anti-inflammatory drugs. They thought to exert their therapeutic effects through multiple mechanisms, including the inhibition of cyclo-oxygenases, modulation NF-κB activity, direct activation AMPK. However, full spectrum activities is incompletely understood. Here we show that salicylate specifically inhibits CBP p300 lysine acetyltransferase activity in vitro by competition with acetyl-Coenzyme A at catalytic site. We a chemical...
Clustered binary data with a large number of covariates have become increasingly common in many scientific disciplines. This paper develops an asymptotic theory for generalized estimating equations (GEE) analysis clustered when the grows to infinity clusters. In this "large $n$, diverging $p$" framework, we provide appropriate regularity conditions and establish existence, consistency normality GEE estimator. Furthermore, prove that sandwich variance formula remains valid. Even working...
Summary Model selection for marginal regression analysis of longitudinal data is challenging owing to the presence correlation and difficulty specifying full likelihood, particularly correlated categorical data. The paper introduces a novel Bayesian information criterion type model procedure based on quadratic inference function, which does not require likelihood or quasi-likelihood. With probability approaching 1, selects most parsimonious correct model. Although working matrix assumed,...
Abstract By allowing the regression coefficients to change with certain covariates, class of varying coefficient models offers a flexible approach modeling nonlinearity and interactions between covariates. This article proposes novel estimation procedure for based on local ranks. The new provides highly efficient robust alternative linear least squares method, can be conveniently implemented using existing R software package. Theoretical analysis numerical simulations both reveal that gain...
Analysis of health care cost data is often complicated by a high level skewness, heteroscedastic variances and the presence missing data. Most existing literature on analysis have been focused modeling conditional mean. In this paper, we study weighted quantile regression approach for estimating quantiles with covariates. The estimator consistent, unlike naive estimator, asymptotically normal. Furthermore, propose modified BIC variable selection in when covariates are at random. framework...
We consider a flexible semiparametric quantile regression model for analyzing high dimensional heterogeneous data. This has several appealing features: (1) By considering different conditional quantiles, we may obtain more complete picture of the distribution response variable given covariates. (2) The sparsity level is allowed to be at levels. (3) partially linear additive structure accommodates nonlinearity and circumvents curse dimensionality. (4) It naturally robust heavy-tailed...
Abstract We introduce a novel approach for high-dimensional regression with theoretical guarantees. The new procedure overcomes the challenge of tuning parameter selection Lasso and possesses several appealing properties. It uses an easily simulated that automatically adapts to both unknown random error distribution correlation structure design matrix. is robust substantial efficiency gain heavy-tailed errors while maintaining high normal errors. Comparing other alternative procedures, it...
Abstract ℓ 1 -penalized quantile regression (QR) is widely used for analysing high-dimensional data with heterogeneity. It now recognized that the ℓ1-penalty introduces non-negligible estimation bias, while a proper use of concave regularization may lead to estimators refined convergence rates and oracle properties as signal strengthens. Although folded penalized M-estimation strongly convex loss functions have been well studied, extant literature on QR relatively silent. The main difficulty...
HCC seriously threatens human health, and the treatment methods are of crucial importance. The tumor microenvironment is critical to origin progression HCC, aberrant regulation immune checkpoint signaling pathway a key method by which cells avoid surveillance. Conventional single-treatment approaches for have drawbacks. Inhibitors PD-1/PD-L1 CTLA-4, together known as "golden combination," primary HCC. Compared with single treatment, it has synergistic effect benefits in boosting response...
Shrinkage-type variable selection procedures have recently seen increasing applications in biomedical research. However, their performance can be adversely influenced by outliers either the response or covariate space. This article proposes a weighted Wilcoxon-type smoothly clipped absolute deviation (WW-SCAD) method, which deals with robust and estimation simultaneously. The new procedure conveniently implemented statistical software R. We establish that WW-SCAD correctly identifies set of...
Abstract For the heteroscedastic nonparametric regression model Y ni =m (x )+σ ) ε , i=1, …, n, we discuss a novel method for testing some parametric assumptions about function m. The test is motivated by recent developments in asymptotic theory analysis of variance when number factor levels large. Asymptotic normality statistic established under null hypothesis and suitable local alternatives. similarity form to that classical F-statistic allows easy fast calculation. Simulation studies...
Abstract ASXL2 is frequently mutated in acute myeloid leukaemia patients with t (8;21). However, the roles of normal haematopoiesis and pathogenesis malignancies remain unknown. Here we show that deletion Asxl2 mice leads to development myelodysplastic syndrome (MDS)-like disease. −/− have an increased bone marrow (BM) long-term haematopoietic stem cells (HSCs) granulocyte–macrophage progenitors compared wild-type controls. Recipients transplanted +/− BM shortened lifespan due MDS-like...
We introduce an R package PGEE that implements the penalized generalized estimating equations (GEE) procedure proposed by Wang et al. (2012) to analyze longitudinal data with a large number of covariates.The includes three main functions: CVfit, PGEE, and MGEE.The CVfit function computes cross-validated tuning parameter for equations.The performs simultaneous estimation variable selection high-dimensional covariates; whereas MGEE fits unpenalized GEE comparison.The is illustrated using yeast...
t(8;21) is one of the most frequent chromosomal abnormalities observed in acute myeloid leukemia (AML). However, expression AML1-ETO not sufficient to induce transformation vivo. Consistent with this observation, patients translocation harbor additional genetic abnormalities, suggesting a requirement for cooperating mutations. To better define landscape AML and distinguish driver from passenger mutations, we compared mutational profiles AML1-ETO-driven mouse models human patients. We...
Summary The problem of estimating the average treatment effects is important when evaluating effectiveness medical treatments or social intervention policies. Most existing methods for effect rely on some parametric assumptions about propensity score model outcome regression one way other. In reality, both models are prone to misspecification, which can have undue influence estimated effect. We propose an alternative robust approach based observational data in challenging situation neither a...
We consider a heteroscedastic regression model in which some of the coefficients are zero but it is not known ones. Penalized quantile useful approach for analysing such data. By allowing different covariates to be relevant modelling conditional functions at levels, provides more complete picture distribution response variable than mean regression. Existing work on penalized has been mostly focused point estimation. Although bootstrap procedures have recently shown effective inference...
The US electrical grid has undergone substantial transformation with increased penetration of wind and solar forms variable renewable energy (VRE). Despite the benefits VRE for decarbonization, it garnered some controversy inducing unwanted effects in regional electricity markets. In this study, role is examined on system price volatility based hourly, real-time, historical data from six independent operators (ISOs) using quantile skew t-distribution regressions. After correcting temporal...