Sitemap

Page Not Found

Page not found. Your pixels are in another canvas.

Research

Statistical methodology for complex, high-dimensional neural data — and the computational tools to make it tractable.

Archive Layout with Content

Podcasts by Category

Podcasts by Collection

CV

Markdown

Page not in menu

This is a page not in th emain menu

Notes

Page Archive

Podcasts

Portfolio

Publications

Repositories

Sitemap

Podcasts by Tags

Talk map

Talks and presentations

Terms and Privacy Policy

Podcasts

Jupyter notebook markdown generator

Spatial Statistics with Sudipto Banerjee (Ep. 1)

less than 1 minute read

Published: December 16, 2021

Bayesian Computing with Andrew Holbrook (Ep. 2)

less than 1 minute read

Published: June 20, 2022

250 Notes

2020

Personal notes from the 250 sequence of classes at UCLA. Notes cover linear algebra, quadratic forms, linear regression, hypothesis testing, inference, optimal design, shrinkage estimators, ANOVA, linear mixed effects models, Gaussian graphical models, and Bayesian regression. Notes

AdaptEllipticalSliceSampler.jl Permalink

A Julia package implementing the adaptive generalized elliptical slice sampler (AGESS), a tuning-free, gradient-free MCMC algorithm for gradient-free Bayesian inference.

Portfolio item number 1

Short description of portfolio item number 1

Portfolio item number 2

Short description of portfolio item number 2

Germline variants disrupting microRNAs predict long-term genitourinary toxicity after prostate cancer radiation (2022)

A.U. Kishan, N. Marco, M.B. Schulz-Jaavall, M.L. Steinberg, P.T. Tran, J.E. Juarez, et al., J.B. Weidhaas

Germline biomarkers predict toxicity to anti-PD1/PDL1 checkpoint therapy (2022)

J. Weidhaas, N. Marco, A.W. Scheffler, A. Kalbasi, K. Wilenius, E. Rietdorf, et al., D. Telesca

Viral burden and clearance in asymptomatic COVID-19 Patients (2022)

A.B. Gunatilaka, N. Marco, G.H. Read, M. Sweeney, G. Regan, C. Tsang, et al., J.B. Weidhaas

Application of a genetic signature of late GU toxicity in SCIMITAR, a Post-op SBRT trial (2023)

A.U. Kishan, N. Marco, T.M. Ma, M.L. Steinberg, A. Sachdeva, M. Cao, L.K. Ballas, E. Rietdorf, D. Telesca, J.B. Weidhaas

Early findings from the GARUDA trial: The impact of a genetic signature of late radiation toxicity on prostate cancer treatment decision making. (2023)

J.B. Weidhaas, N. Marco, M.L. Steinberg, A. Lee, M. Xiang, L.F. Valle, M. Casado, A. Stube, D. Telesca, A.U. Kishan

Functional Mixed Membership Models (2024)

N. Marco, D. Şentürk, S. Jeste, C. DiStefano, A. Dickinson, D. Telesca

Flexible Regularized Estimation in High-Dimensional Mixed Membership Models (2024)

N. Marco, D. Şentürk, S. Jeste, C.C. DiStefano, A. Dickinson, D. Telesca

Modeling Neural Switching via Drift-Diffusion Models (2024)

N. Marco, J.M. Groh, S.T. Tokdar

Bayesian Covariance Regression in Functional Data Analysis with Applications to Functional Brain Imaging (2025)

J. Shamshoian, N. Marco, D. Şentürk, S. Jeste, D. Telesca

Germline microRNA-based signatures predict toxicity and response to anti-CTLA-4 therapy (2025)

J.B. Weidhaas, K.M. McGreevy, N. Marco, N. Sundahl, C.R. Cabanski, C. Spencer, T. LaVallee, P. Ost, D. Telesca

Covariate Adjusted Functional Mixed Membership Models (2025)

N. Marco, D. Şentürk, S. Jeste, C. DiStefano, A. Dickinson, D. Telesca

Germline Radiosensitivity Biomarker for Radiation-Induced GU Toxicity Following Radiation Therapy in Localized Prostate Cancer (GARUDA): Two-Year Outcomes of a Phase II Clinical Trial (2026)

J.E. Juarez Casillas, P. Jamshidian, M.U. Casado, K. Flores, N. Marco, M.L. Steinberg, A. Lee, M. Xiang, L.F. Valle, A. Stube, D. Telesca, J.B. Weidhaas, A.U. Kishan

Mixed Membership Models for Multilevel Functional Data (2026)

D. Telesca, N. Marco, E. Landry

Adaptive Generalized Elliptical Slice Sampling (2026)

N. Marco, S.T. Tokdar

Bayesian Functional Partial Membership Models

Published: June 24, 2021

We propose a model which allows for each observation to partially belong to multiple clusters. In this model, we assume that each observation is functional. We assume an additive model with respect to the cluster membership. In order to reduce the number of parameters, we use a covariance function that is inspired by Multivariate Functional Principal Component Analysis.