Official websites use .gov

A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS

A lock ( 🔒 ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Need Help

Advancing Exponential-Family Random Graph Model Estimation and Power Analysis for Biomedical and Public Health Research

Award Number: R21LM015164
ORGANIZATION: NATIONAL LIBRARY OF MEDICINE
OPDIV: NIH
AWARD CLASS: DISCRETIONARY
AWARD ACTIVITY TYPE: SCIENTIFIC/HEALTH RESEARCH (INCLUDES SURVEYS)
PERIOD OF PERFORMANCE START DATE: 09/10/2026
PERIOD OF PERFORMANCE END DATE: 09/09/2028

Group Awards By:

View Award Description

Advancing Exponential-Family Random Graph Model Estimation and Power Analysis for Biomedical and Public Health Research - Summary/Abstract Exponential-family Random Graph Models [ERGMs] are a powerful statistical framework for analyzing com- plex networks, with applications in epidemiology, social sciences, genomics, and neuroscience. However, their broader adoption is hindered by persistent methodological challenges, particularly in estimation stability and power analysis for multi-network studies. Current estimation techniques often fail to converge when applied to real-world networks with high complexity, limiting their reliability. Additionally, there is no established framework for power analysis in multi-network ERGM studies, making study design and reproducibility difficult. This project directly addresses these critical gaps by developing (1) a novel Conditional ERGM Seeding approach to im- prove estimation stability and convergence, and (2) the first power analysis framework tailored to ERGM-based multi-network studies. We will achieve these objectives through two specific aims. Aim 1 will develop, validate, and implement Conditional ERGM Seeding to improve parameter estimation, ensuring more stable and reliable convergence in computationally challenging networks. Aim 2 will create a comprehensive power analysis framework for multi- network ERGMs, equipping researchers with the tools necessary to optimize study design and ensure statistical rigor. Both methods will be integrated into user-friendly R software packages, ergm.cond and ergm.power, which will be openly disseminated via CRAN and GitHub. This work aligns with the NIH Office of Data Science Strategy (ODSS) mission to advance computational methodologies that enhance data transparency, reproducibility, and accessibility. By addressing key computa- tional barriers in network science, this project will improve the scalability and robustness of ERGMs, making them more accessible to researchers in biomedical, public health, and social sciences. The proposed methods will directly impact how complex networks are studied, leading to more reliable inference, better study design, and greater reproducibility in network-based research.


Issue Date FY	Funding FY	Legal Entity Name	Legal Entity Address	Legal Entity City	Legal Entity State	Legal Entity Zip Code	Legal Entity COUNTY	Legal Entity COUNTRY	Assistance Listing	Award Code	Budget Year	Action Date	Action Type	Action Amount

Issue Date FY: 2026 ( Subtotal = $361,710 )
2026	2026	UNIVERSITY OF UTAH	201 PRESIDENTS CIR	SALT LAKE CITY	UT	84112	SALT LAKE	USA	Medical Library Assistance	000	1	9/11/2026	NEW	$361,710
														Subtotal = $361,710

Grand Total All Awards = $361,710

Top

All Categories

About

Search

Reports

Data Submission

Award Information

Advancing Exponential-Family Random Graph Model Estimation and Power Analysis for Biomedical and Public Health Research

Award Number: R21LM015164

ORGANIZATION: NATIONAL LIBRARY OF MEDICINE

OPDIV: NIH

AWARD CLASS: DISCRETIONARY

AWARD ACTIVITY TYPE: SCIENTIFIC/HEALTH RESEARCH (INCLUDES SURVEYS)

PERIOD OF PERFORMANCE START DATE: 09/10/2026

PERIOD OF PERFORMANCE END DATE: 09/09/2028

Federal Websites

Department of Health & Human Services

HHS Operating Divisions

HHS Staff Divisions

Download A Document Viewer