Schedule

Regular meeting time: Every other Thursday 12:15 - 1:15 pm, Fishbowl Conference Room (UOP 2-254) or online

October 2 (12:15 - 1:15 PM, UOP 2-254 Fishbowl Conf Rm, hybrid)

Presenter: Han Lu

Topic: Restricted Mean Survival Time (RMST), which is the area under the survival curve from time 0 to a restricted time tau, is gaining research popularity as it offers an alternative summary to proportional hazard-based models in comparing treatment effects for clinical trials. However, how to choose the restricted time tau? This paper explores a data-driven way to find the optimal restricted time considering effect size and estimation precision at the same time.

Reference:  Beyond Fixed Restriction Time: Adaptive Restricted Mean Survival Time Methods in Clinical Trials by Drs. Jinghao Sun, Douglas Schaubel, and Eric Tchetgen Tchetgen

October 16 Postponed to October 23 (12:15 - 1:15 PM, UOP 2-254 Fishbowl Conf Rm, hybrid)

Presenter: Dr. Anne Eaton 

Topic: How to test and conclude the treatment effects when two survival curves are expected to cross at a certain time? This paper proposes statistical methods for comparing treatments when survival curves cross, focusing on detecting differences in long-term survival after a prespecified time point. 

Reference: Comparing Treatments in the Presence of Crossing Survival Curves: An Application to Bone Marrow Transplantation, Logan, Klein, and Zhang (2008)

October 30 (12:15 - 1:15 PM, UOP 2-254 Fishbowl Conf Rm, hybrid)

Presenter: Caleb Griffiths

Topic: Our division's Ph.D. student, Caleb, will present an overview of the pseudo-observations. 

Reference: Pseudo-observations in survival analysis, Andersen and Perme (2009)

November 14 (11 AM -1 PM, UOP 2-274 Student Collaboration Rm)

Note: this is NOT our usual meeting time! We moved the usual meeting to Friday to watch a webinar together. 

Title: Statistical analysis with the occurrence of a terminal event

Speaker: Bin Nan, Ph.D., Chancellor's Professor, Department of Statistics, UC Irvine 

Sponsor: Lifetime Data Science Section (ASA)

Abstract: In cohort studies, time plays important roles in data collection and data analysis. Two distinct sets of statistical tools have been developed primarily for analyzing data in cohort studies: one is longitudinal data analysis that focuses on properly handling temporal dependence among repeatedly collected measurements over time, one is survival analysis that deals with time-to-event data when censoring occurs. In this webinar, I will present some recently developed more interpretable work on analyzing data in cohort studies in a particular situation: a terminal event occurs.

For analyzing longitudinal data with the occurrence of a terminal event that is subject to right censoring, I will first introduce the idea of conditional modeling given the terminal event time (usually death time) via a parametric model, then extend it to a more robust nonparametric bivariate time-varying coefficient model in which the time-varying coefficients capture the longitudinal trajectories of covariate effects along with both the follow-up time and the residual lifetime.

For analyzing time-to-event data, e.g. disease onset, with the occurrence of a terminal event, in contrast to the commonly used semi-competing risks or illness-death model, I will introduce a nonparametric estimation of the distribution of the disease onset time conditional on the death time, which consists of two components that provide straightforward interpretations of the disease onset during the lifespan. Regression models are constructed for these two components when evaluating risk factors of disease onset is of interest.

All these statistical developments are motivated by real studies. In addition to presenting statistical properties and simulation results, I will also present the results of several data examples analyzed by the proposed methods.

References:

Conditional modeling of longitudinal data with terminal event, Kong et al. (2019).

Kernel Estimation of Bivariate Time-varying Coefficient Model for Longitudinal Data with Terminal Event, Wang, Nan, and Kalbfleisch (2025).

November 27

No meeting on Thanksgiving - Happy Holiday!

December 5 - Pop-Up Meeting (9-10 AM, UOP 2-254 Fishbowl Conf Rm)

Note: this is NOT our usual meeting time! We hold this pop-up meeting to watch a webinar together.

Title: A Unified Approach to Covariate Adjustment for Survival Endpoints in Randomized Clinical Trials

Speaker: Dr. Zhiwei Zhang from Gilead Sciences

Sponsor: ISBS (The International Society For Biopharmaceutical Statistics) Webinar Series

Abstract: Covariate adjustment aims to improve the statistical efficiency of randomized trials by incorporating information from baseline covariates. Popular methods for covariate adjustment include analysis of covariance for continuous endpoints and standardized logistic regression for binary endpoints. For survival endpoints, while some covariate adjustment methods have been developed for specific effect measures, they are not commonly used in practice for various reasons, including high demands for theoretical and methodological sophistication as well as computational skills. This article describes an augmentation approach to covariate adjustment for survival endpoints that is relatively easy to understand and widely applicable to different effect measures. This approach involves augmenting a given treatment effect estimator in a way that preserves consistency and asymptotic normality under minimal assumptions (i.e., randomization). It does not attempt to exploit other possible constraints (e.g., independent censoring, proportional hazards) on the observed data distribution. The optimal augmentation term, which minimizes the asymptotic variance of an augmented estimator, can be estimated using various statistical and machine learning methods. Simulation results demonstrate that the augmentation approach can bring substantial gains in statistical efficiency.

Webinar link (if you cannot attend the working group meeting), with meeting ID 818 1401 5856 and passcode 844889.

December 11

Topic: No separate end-of-semester social event will be scheduled due to the Division's Winter Recognition Event at noon.

Spring 2026, event in scheduling

Presenter: Dr. Tianmeng Lyu

Topic (tentative): Restricted mean survival time (RMST) estimation in a clinical trial with a composite endpoint of an interval-censored event (e.g., progression) and right-censored death, benefits by converting the composite endpoint to interval censoring. 

Reference:  Gao et al. (2025), RMST for Interval-Censored Data in Oncology Clinical Trials