Please join the Washington Statistical Society (WSS) on May 29th for the 2024 Gertrude Cox Lecture and Reception. Congratulations to Tanya Garcia, Associate Professor of Biostatistics at the University of North Carolina, Chapel Hill. The Award is co-sponsored by the WSS and RTI International and the lecture and reception will be hosted in-person at Mathematica. Registration is required and information for in-person attendance is below. There is a virtual option for those wishing to attend virtually. Please see the attached flyer for more information.
2024 Gertrude M. Cox Lecture and Reception
Sponsored by the Washington Statistical Society and RTI International
When: Wednesday, May 29th, 2024, 3:00 – 5:00 PM
Where: Mathematica Conference Center (Virtual option available)
1100 First ST NE, 12th Floor. Near Noma-Gallaudet Metro Station (Red Line) or PMI Parking Garage
In-Person Registration (EventBrite): https://www.eventbrite.com/e/2024-washington-statistical-society-gertrude-m-cox-lecture-and-reception-tickets-899394883307?aff=oddtdtcreator
Remote Registration (WebEx): https://mathematicaorg.webex.com/weblink/register/r2de6893b181edda499e2d847064e7fa9
The Missing Link: Establishing the Parallels Between Censored Covariate and Missing Data
Tanya Garcia is the 2024 Gertrude M. Cox Award recipient. Dr. Garcia is an Associate Professor of Biostatistics, Provost Distinguished Faculty Leader, and Tyson Academic Leader at the University of North Carolina at Chapel Hill (UNC-CH). For over a decade, she has led a transdisciplinary research team of statisticians and neuroscientists toward designing robust statistical methods for neurodegenerative diseases. Dr. Garcia combines her excitement for modeling with her interest in training the next generation of (bio)statisticians to embrace a growth mindset and tackle obstacles without judgment or fear. How she mentors this next generation is largely motivated by 500+ hours of grantsmanship and leadership training. Her desire for every mentee to achieve success and fulfillment drives her every leadership decision. These decisions have led Dr. Garcia to not only maintain continuous funding of multiple grants as Principal Investigator from the National Institutes of Health, but also coach thirty-four mentees and counting to achieve over 70 awards, grants, and fellowships. In addition to the 2024 Gertrude M. Cox Award, Dr. Garcia has also received numerous competitive awards, including the 2022 Carolina Women's Leadership Council Faculty Mentoring Award from UNC-CH.
Abstract: While right-censored time-to-event outcomes have been studied for decades, handling time-to-event covariates, also known as censored covariates, is now of growing interest. So far, the literature has treated right-censored covariates as distinct from missing covariates, overlooking the potential applicability of estimators across both scenarios. We bridge this gap by establishing connections between right-censored and missing covariates under various assumptions about censoring and missingness, allowing us to identify parallels and determine when estimators can be transferred between the two contexts. This connection reveals five new estimators for right-censored covariates in the unexplored area of informative covariate censoring, where the event time depends on censoring time. We evaluate the robustness of these five estimators under incorrect distributional assumptions and establish efficiency comparisons. We further present their asymptotic properties and propose a hypothesis test for assessing if the covariate censoring is informative or not. Empirical studies demonstrate the robustness and efficiency properties of each estimator. All estimators are applied to a Huntington disease observational study to analyze cognitive impairment as a function of time to clinical diagnosis.
------------------------------
Jeffrey Gonzalez, PhD (he/him/his)
Director, Mathematical Statistics Research Center
Office of Survey Methods Research
U.S. Bureau of Labor Statistics
------------------------------