Skip to main content

Search NYU Steinhardt

Marginal Structural Models for Causal Inference with Continuous-Time Treatments

PRIISM seminar speaker Liangyuan Hu
11:00am-12:00pm ET
Cost:
FREE
Apr
14

PRIISM Seminar by Mount Sinai School of Medicine's Liangyuan Hu

Wednesday, April 14, 2021

11:00 am - 12:00 pm ET

Zoom (the recording of this seminar will posted on our website)

RSVP for Zoom Link

Marginal Structural Models for Causal Inference with Continuous-Time Treatments

Join us and Dr. Liangyuan Hu to learn how causal inference models can help improve health treatments for HIV, COVID-19 and cardiovascular diseases. 

Abstract

Public health research often involves evaluating the effects of continuous-time treatments. Causal inference has traditionally focused on the estimation of causal effects of a number of treatments defined at baseline. In the case where treatment assignment is time-dependent, the treatment is often categorized in terms of time intervals for treatment initiation. This categorization can lead to the coarsening of information on treatment initiation and fails to answer the question of the causal effect of actual treatment timing. The marginal structural model, pioneered by Robins and colleagues, has been widely used for causal inference. It is easy to implement and provides a general infrastructure for the weighting based methods to address confounding, particularly time-varying confounding. In this talk, Dr. Hu will show how the marginal structural model can be used to capture the causal effect of the continuous-time treatment when treatment initiation is either static or dynamic. Dr. Hu will derive estimation strategies amenable to marginal structural models to overcome complications frequently encountered in observational healthcare data, including incomplete treatment initiation time and censored survival outcomes. A case study applying our approaches to a large-scale electronic health record data will estimate the optimal antiretroviral therapy initiating rules for patients presenting with HIV/TB coinfection and HIV-infected adolescents. New insights that can be gained relative to findings from randomized trials will be discussed. Finally, Dr. Hu will discuss how the methods can be used and extended to address important emerging questions related to cardiovascular and COVID-19 diseases.

Bio

Liangyuan Hu is an Assistant Professor of Biostatistics in the Department of Population Health Science & Policy at Mount Sinai School of Medicine. She received her PhD in Biostatistics from Brown University in 2015. Her research interests include statistical methods for causal inference, missing data and Bayesian machine learning, with applications in cancer, HIV and cardiovascular diseases. Her work in causal inference has won the prestigious Outstanding Statistical Application Award from the American Statistical Association in 2019.

Please note this virtual event requires an internet connection and computer, tablet, or smartphone. It is a priority to make our events inclusive and accessible and PRIISM is pleased to provide accommodations for people with disabilities. Requests for accommodations for events and services should be submitted at least two weeks before the date of the accommodation need. Please email Susana Toro Isaza (susana.toro@nyu.edu) for assistance.

Many of our online events will be closed captioned and posted on the PRIISM YouTube page.

NYU provides reasonable accommodations to people with disabilities. Please submit your request for accommodations for events and services at least two weeks before the date of your accommodation need. Although we can't guarantee accommodation requests received less than two weeks before the event, you should still contact us and we will do our best to meet your accommodation need. Please email Contact Us for assistance.