2023 Spring Meetings

Spring Semester, 2023

February 13 (a talk on risk prediction):

Invited by the Pediatrics Department, Dr. Yan Yuan from University of Alberta will give a talk, "Risk Prediction for Premature Menopause in Childhood Cancer Survivors" on Monday, Feb. 13, 2023 (10:00-11:00 am). Zoom link: https://umn-private.zoom.us/j/98571319969?pwd=SUMybkczZExMU2xtcGhYcXIzOE1Fdz09

References: You can read Dr. Yuan's acute ovarian failure risk calculator paper before the talk: https://doi.org/10.1016/S1470-2045(19)30818-6. Here is the link to the calculator developed: https://ccss.stjude.org/tools-documents/calculators-other-tools/ccss-ovarian-risk-calculator.html 

February 24:

Our first SAWG meeting in the Spring semester is led by Dr. Benjamin Langworthy. He will present "Principal components analysis for right censored data."

References: Langworthy BW, Cai J, Corty RW, Kosorok MR and Fine JP. Principal components analysis for right censored data. Statistica Sinica (accepted).

(March 10, Spring Break, no meeting)

March 17: 

Ph.D. student Han Lu will talk about accelerated failure time model. Slides can be found here.

References: 

• Wei LJ. (1992). The accelerated failure time model: A useful alternative to the cox regression model in survival analysis. Statistics in Medicine, 11:1871-1879.

• Jin Z, Lin DY, Wei LJ, Ying Z. (2003). Rank‐based inference for the accelerated failure time model. Biometrika, 90:341–353.

March 31:

We have invited our Biostat alum, Dr. Tianmeng Lyu to give a talk on her newly published Biometrics paper, "Bayesian inference for a principal stratum estimand on recurrent events truncated by death". Slides can be found here.

References: Tianmeng Lyu, Björn Bornkamp, Guenther Mueller-Velten, Heinz Schmidli. Bayesian inference for a principal stratum estimand on recurrent events truncated by death. Biometrics; first published: 17 January 2023; https://doi.org/10.1111/biom.13831

April 7: 

Ph.D. student Han Lu will introduce the idea of survival random forest and present a tutorial on an R package, randomFrestSRC, to implement the method. This is a popular one for variable selection in survival analysis! Slides can be found here.

Reference: The homepage for the R package randomFrestSRC is: https://www.randomforestsrc.org/

Useful links from discussions: 

• Wicklin R. The average bootstrap sample omits 36.8% of the data, SAS Blogs, June 28, 2017.

• Efron B and Tibshirani R. (1997). Improvements on Cross-Validation: The .632+ Bootstrap Method. JASA, 92 (438):548-560.

April 17: 

We can watch UPenn Conference's on Advances in Time-to-Event Analyses in Clinical Trials together in the CCBR. Our own Dr. Anne Eaton will give a presentation in the afternoon session! If you want to watch the conference on your own (or even go to the conference in person in Philadelphia), here is the registration link.

Agenda:

8-8:30 Devan Mehrotra: Overview: Non-Proportional Hazards and Composite Endpoints (Reference)

8:30 Lu Tian: On estimating the survival distribution of the duration of response (Reference)

8:55 Zhenzhen Xu: Design of immuno-oncology studies involving biomarker-defined subgroups (Reference)

9:20 Fan Li: Multiply robust estimation of causal effects with noncompliance and time-to-event outcomes

10:15-11:00 Panel Discussion: (Pamela Shaw, PhD, Kaiser Permanente WHRI – AM Online Facilitator)

Pralay Mukhopadhyay, PhD, Otsuka Pharmaceutical

Douglas Schaubel, PhD, University of Pennsylvania

Mei-Cheng Wang, PhD, Johns Hopkins

12:50 Terry Therneau: Multi-state models for trial data

1:15 Lu Mao: Non- and semi-parametric analysis of composite time-to-event endpoints

1:40 Anne Eaton: Statistical approaches for component-wise censored composite endpoints (Reference 1, Reference 2)

2:05 Richard Cook: Estimands in clinical trials with complex life history processes (Reference)

2:45-3:30 Panel Discussion: (Bryan Blette, PhD, University of Pennsylvania – PM Online Facilitator)

Ionut Bebu, PhD, George Washington University

Rebecca Betensky, PhD, New York University

Michael Fay, PhD, National Institute of Allergy and Infectious Diseases

4:00-4:10 Closing Remarks (Mary Putt, ScD, Chair Organizing Committee)

April 21: 

Our own Andrés Arguedas will lead this meeting. He wanted to introduce the idea of landmarking and joint modelling: what they're used for, how they differ, how they perform, mentioning some R packages that can do it, etc. So the first part of the talk would be mostly focused on this introduction, and then for the second part pivot to talking about a specific paper that compares both of these methods:

Reference: Krithika Suresh, Jeremy M G Taylor, Daniel E Spratt, Stephanie Daignault, Alexander Tsodikov. Comparison of joint modeling and landmarking for dynamic prediction under an illness-death model. Biom J. 2017 Nov;59(6):1277-1300.

April 28: 

Connor Demorest will give a talk on "Survival analysis in cancer and beyond" as a test run for his presentation at Data Tech 2023 in June.

Reference:

• Fine JP, Gray RJ. A proportional hazards model for the subdistribution of a competing risk. J Am Stat Assoc. 1999;94(446):496–509.

• Kalbfleisch, J. D., Prentice, R. L. (2002). The Statistical Analysis of Failure Time Data. John Wiley & Sons.

May 5: 

Dr. Biyue Dai will present "Cross-validation Approaches for Penalized Cox Regression".

Reference: https://arxiv.org/abs/1905.10432