A5101543967- Statistical Methods and Inference
- Advanced Causal Inference Techniques
- Statistical Methods and Bayesian Inference
- Functional Brain Connectivity Studies
- Muscle metabolism and nutrition
- Advanced Statistical Methods and Models
- Advanced Neuroimaging Techniques and Applications
- Dementia and Cognitive Impairment Research
- Alzheimer's disease research and treatments
- Nutritional Studies and Diet
- Folate and B Vitamins Research
- Bayesian Modeling and Causal Inference
- Advanced MRI Techniques and Applications
- Sparse and Compressive Sensing Techniques
- Clinical Nutrition and Gastroenterology
- Diet and metabolism studies
- Face and Expression Recognition
- Health Systems, Economic Evaluations, Quality of Life
- Genetic Associations and Epidemiology
- Bioinformatics and Genomic Networks
- Long-Term Effects of COVID-19
- Liver Disease Diagnosis and Treatment
- Neural Networks and Applications
- Osteoarthritis Treatment and Mechanisms
- Nutrition, Health and Food Behavior
University of Toronto
2017-2025
University of South China
2024
University of North Carolina at Chapel Hill
2015-2016
Decision Systems (United States)
2015
Communities In Schools of Orange County
2015
Arizona State University
2015
North Carolina State University
2014
In modern experiments, functional and nonfunctional data are often encountered simultaneously when observations sampled from random processes high-dimensional scalar covariates. It is difficult to apply existing methods for model selection estimation. We propose a new class of partially linear models characterize the regression between response covariates both types. The approach provides unified flexible framework that takes into account multiple ultrahigh-dimensional predictors, enables us...
Summary We consider a functional linear Cox regression model for characterizing the association between time-to-event data and set of scalar predictors. The incorporates principal component analysis modeling predictors high-dimensional to characterize joint effects both on data. develop an algorithm calculate maximum approximate partial likelihood estimates unknown finite infinite dimensional parameters. also systematically investigate rate convergence score test statistic testing nullity...
We extend four tests common in classical regression – Wald, score, likelihood ratio and F to functional linear regression, for testing the null hypothesis, that there is no association between a scalar response covariate. Using principal component analysis, we re-express model as standard model, where effect of covariate can be approximated by finite combination scores. In this setting, consider application traditional tests. The proposed procedures are investigated theoretically densely...
The aim of this article is to develop a low-rank linear regression model correlate high-dimensional response matrix with vector covariates when coefficient matrices have structures. We propose fast and efficient screening procedure based on the spectral norm each deal case number extremely large. an estimation trace regularization, which explicitly imposes low rank structure matrices. When both dimension that covariate diverge at exponential order sample size, we investigate sure...
The growing public threat of Alzheimer's disease (AD) has raised the urgency to quantify degree cognitive decline during conversion process mild impairment (MCI) AD and its underlying genetic pathway. aim this article was test common variants associated with accelerated after MCI AD.In 583 subjects enrolled in Disease Neuroimaging Initiative (ADNI; ADNI-1, ADNI-Go, ADNI-2), 245 participants converted at follow-up. We tested interaction effects between individual single-nucleotide...
Unmeasured confounding presents a significant challenge in causal inference from observational studies. Classical approaches often rely on collecting proxy variables, such as instrumental variables. However, applications where the effects of multiple treatments are simultaneous interest, finding sufficient number variables for consistent estimation treatment can be challenging. Various methods literature exploit structure to address unmeasured confounding. In this paper, we introduce novel...
Single-cell trajectory analysis aims to reconstruct the biological developmental processes of cells as they evolve over time, leveraging temporal correlations in gene expression. During cellular development, expression patterns typically change and vary across different cell types. A significant challenge this is that RNA sequencing destroys cell, making it impossible track multiple stages for same cell. Recent advances have introduced use optimal transport tools model individual cells. In...
Job stability - encompassing secure contracts, adequate wages, social benefits, and career opportunities is a critical determinant in reducing monetary poverty, as it provides households with reliable income enhances economic well-being. This study leverages EU-SILC survey census data to estimate the causal effect of job on poverty across Italian provinces, quantifying its influence analyzing regional disparities. We introduce novel small area estimation (CSAE) framework that integrates...
The aim of this paper is to develop a Bayesian functional linear Cox regression model (BFLCRM) with both and scalar covariates. This new development motivated by establishing the likelihood conversion Alzheimer's disease (AD) in 346 patients mild cognitive impairment (MCI) enrolled Disease Neuroimaging Initiative 1 (ADNI-1) early markers conversion. These MCI were followed over 48 months, 161 participants progressing AD at months. was used establish that covariates including hippocampus...
Recent advances in single-cell sequencing technology have provided opportunities for mathematical modeling of dynamic developmental processes at the level, such as inferring trajectories. Optimal transport has emerged a promising theoretical framework this task by computing pairings between cells from different time points. However, optimal methods limitations capturing nonlinear trajectories, they are static and can only infer linear paths endpoints. In contrast, stochastic differential...
The growing public threat of Alzheimer's disease (AD) has raised the urgency to discover and validate prognostic biomarkers in order predicting time onset AD. It is anticipated that both whole genome single nucleotide polymorphism (SNP) data high dimensional brain imaging fer predictive values identify subjects at risk for progressing aim this paper test whether SNP offer In 343 with mild cognitive impairment (MCI) enrolled Disease Neuroimaging Initiative (ADNI-1), we extracted MR...
Abstract Causal inference has been increasingly reliant on observational studies with rich covariate information. To build tractable causal procedures, such as the doubly robust estimators, it is imperative to first extract important features from high or even ultra-high dimensional data. In this paper, we propose ball screening for confounder selection modern data sets. Unlike familiar task of variable prediction modeling, our procedure aims control confounding while improving efficiency in...