A5049635087- Statistical Methods and Inference
- Advanced Statistical Methods and Models
- Retinopathy of Prematurity Studies
- Image and Signal Denoising Methods
- Control Systems and Identification
- Medical Image Segmentation Techniques
- Fault Detection and Control Systems
- Ocular Oncology and Treatments
- Bayesian Methods and Mixture Models
- Neonatal and fetal brain pathology
- Neural Networks and Applications
- Probabilistic and Robust Engineering Design
- Neonatal Respiratory Health Research
- Bayesian Modeling and Causal Inference
- Sparse and Compressive Sensing Techniques
- Statistical and numerical algorithms
- Advanced MRI Techniques and Applications
- Soil Geostatistics and Mapping
- Advanced Neuroimaging Techniques and Applications
- Retinal Diseases and Treatments
- Adversarial Robustness in Machine Learning
- Anomaly Detection Techniques and Applications
- Retinal Development and Disorders
- Cancer-related Molecular Pathways
- Complex Network Analysis Techniques
University of California, Davis
2015-2024
California University of Pennsylvania
2024
Children's Hospital of Los Angeles
2012-2023
Southern California Eye Institute
2014-2023
University of Southern California
2009-2023
Catholic University of America
2020
Brigham and Women's Hospital
2013-2020
University of Notre Dame
2020
National Bureau of Economic Research
2020
U.S. Energy Information Administration
2020
This book interweaves inferential approaches and theory practice in econometrics. Basic statistical linear algebra concepts are introduced as they needed to give life the model under study. Most econometric applications start with a tentative or hypothesis sample of data goal learning something about phenomena study from limited set observations. Therefore that may be used investigate particular economic is presented motivate analysis each models presented. linkage between process thought...
AbstractThis article considers the problem of modeling a class nonstationary time series using piecewise autoregressive (AR) processes. The number and locations AR segments, as well orders respective processes, are assumed unknown. minimum description length principle is applied to compare various segmented fits data. goal find “best” combination lengths Such implicitly defined optimizer an objective function, genetic algorithm implemented solve this difficult optimization problem. Numerical...
To report an anatomic change following subretinal injection of voretigene neparvovec-rzyl (VN) for RPE65-mediated Leber congenital amaurosis. Multicenter, retrospective chart review. Patients who underwent VN at each 4 participating institutions. were identified as having perifoveal chorioretinal atrophy if (1) the areas not directly related to touch-down site cannula; and (2) area progressively enlarged over time. Demographic data, visual acuity, refractive error, fundus photographs, OCT,...
To evaluate outcomes of Group D eyes bilateral retinoblastoma patients treated with primary chemoreduction and external beam radiation as salvage.Retrospective chart review diagnosed designated in at least one eye from January 1, 2000 to December 31, 2009. Overall, 62 49 were included; 13 had disease. Primary vincristine, etoposide, carboplatin local consolidation was administered, followed by the form intensity-modulated therapy (IMRT) salvage for recurrent tumor. outcome measure globe...
Summary The paper considers the computer model calibration problem and provides a general frequentist solution. Under framework proposed, data is semiparametric with non-parametric discrepancy function which accounts for any between physical reality model. In an attempt to solve fundamentally important (but often ignored) identifiability issue parameters function, proposes new identifiable parameterization of problem. It also develops two-step procedure estimating all relevant quantities...
Summary We propose an iterative estimation procedure for performing functional principal component analysis. The aims at or longitudinal data where the repeated measurements from same subject are correlated. An increasingly popular smoothing approach, penalized spline regression, is used to represent mean function. This allows straightforward incorporation of covariates and simple implementation approximate inference procedures coefficients. For handling within-subject correlation, we...
To determine whether earlier treatment of high-risk, prethreshold retinopathy prematurity (ROP) improves retinal structural outcome at 2 years age.Infants with bilateral high-risk ROP had one eye randomly assigned to peripheral ablation. The fellow was managed conventionally, and either treated threshold or observed if never reached. In patients asymmetrical disease, the randomised conventional management. At age, children were examined comprehensively by certified ophthalmologists outcomes...
Journal Article Model-Assisted Survey Regression Estimation with the Lasso Get access Kelly S. McConville, McConville *Address correspondence to Department of Mathematics and Statistics, Swarthmore College, 500 College Ave, Swarthmore, PA, 19091, USA; E-mail: kmcconv1@swarthmore.edu Search for other works by this author on: Oxford Academic Google Scholar F. Jay Breidt, Breidt Thomas C. M. Lee, Lee Gretchen G. Moisen Statistics Methodology, Volume 5, Issue 2, June 2017, Pages 131–158,...
To investigate late retinal findings and complications of eyes with a history retinopathy prematurity (ROP) that did not meet treatment criteria receive during infancy.
Purpose To demonstrate the use of anatomic MRI‐visible three‐dimensional (3D)‐printed phantoms and to assess process accuracy material MR signal properties. Methods A cervical spine model was generated from computed tomography (CT) data 3D‐printed using an signal‐generating material. Printed phantom characteristics were assessed 120 kVp CT 3 Tesla (T) imaging. The relaxation rates diffusion coefficient fabricated measured 1 H spectra acquired provide insight into nature proton signal....
Abstract. This article considers the problem of detecting break points for a nonstationary time series. Specifically, series is assumed to follow parametric nonlinear time‐series model in which parameters may change values at fixed times. In this formulation, number and locations are unknown. The minimum description length (MDL) used as criterion estimating points, each segment. best segmentation found by minimizing MDL obtained using genetic algorithm. implementation approach illustrated...
This paper proposes an information theory approach to estimate the number of changepoints and their locations in a climatic time series. A model is introduced that has unknown allows for series autocorrelations, periodic dynamics, mean shift at each changepoint time. An objective function gauging locations, based on minimum description length (MDL) criterion, derived. genetic algorithm then developed optimize function. The methods are applied analysis century monthly temperatures from...
<b>Background and study aims: </b>Endoscopic bilateral drainage for inoperable malignant hilar biliary strictures (HBS) using metal stents is considered to be technically difficult. Furthermore, endoscopic revision of stenting after occlusion can challenging. This was performed evaluate the long-term efficacy stent-in-stent placement cross-wired metallic in high-grade HBS planned revision. <b>Patients methods:</b> A total 84 patients with were enrolled from three academic tertiary referral...
In Brief Purpose: The purpose of this study was to document the hand-held spectral domain optical coherence tomography (HHSD-OCT, Bioptigen, Durham, NC) findings in shaken-baby syndrome (SBS). nonaccidental trauma SBS has been associated with retinal findings, including hemorrhages all layers retina and retinoschisis. Methods: Three consecutive patients presumed underwent complete ocular examination, fundus photography RetCam (Clarity Medical Systems, Pleasanton, CA), imaging HHSD-OCT....