scispace - formally typeset
Y

Yimei Li

Researcher at St. Jude Children's Research Hospital

Publications -  23
Citations -  480

Yimei Li is an academic researcher from St. Jude Children's Research Hospital. The author has contributed to research in topics: Regression analysis & Smoothing. The author has an hindex of 10, co-authored 23 publications receiving 419 citations. Previous affiliations of Yimei Li include Columbia University & University of North Carolina at Chapel Hill.

Papers
More filters
Journal ArticleDOI

Intrinsic Regression Models for Positive-Definite Matrices With Applications to Diffusion Tensor Imaging

TL;DR: The intrinsic regression model, which is a semiparametric model, uses a link function to map from the Euclidean space of covariates to the Riemannian manifold of positive-definite matrices, and develops an estimation procedure to calculate parameter estimates and establish their limiting distributions.
Journal ArticleDOI

Multiscale adaptive regression models for neuroimaging data

TL;DR: In this article, a multiscale adaptive regression model (MARM) is proposed to integrate the propagation-separation (PS) approach with statistical modeling at each voxel for spatial and adaptive analysis of neuroimaging data from multiple subjects.
Journal Article

Multiscale adaptive regression models for neuroimaging data

TL;DR: A multiscale adaptive regression model (MARM) is proposed to integrate the propagation-separation approach with statistical modeling at each voxel for spatial and adaptive analysis of neuroimaging data from multiple subjects and significantly outperforms conventional analyses of imaging data.
Journal ArticleDOI

Asymmetrical lateral ventricular enlargement in Parkinson's disease.

TL;DR: This study explored the presence of asymmetrical lateral ventricular enlargement associated with motor asymmetry in Parkinson’s disease and found no evidence of an inverse relationship between these associations and disease progression.
Journal ArticleDOI

Multiscale adaptive generalized estimating equations for longitudinal neuroimaging data.

TL;DR: A powerful propagation-separation procedure is adapted to sequentially incorporate the neighboring information of each voxel and develop a new novel strategy to solely update a set of parameters of interest, while fixing other nuisance parameters at their initial estimators.