2019 LiDS Conference



2019 Conference on Lifetime Data Science: Foundations and Frontiers
The 2nd Conference on Lifetime Data Science
University of Pittsburgh
Pittsburgh, Pennsylvania, USA
May 29 - 31, 2019

The Lifetime Data Science Section of the American Statistical Association is pleased to announce that the conference on Lifetime Data Science: Foundations and Frontiers which will be held at the University of Pittsburgh from May 29, 2019 to May 31, 2019. The event will begin with short courses by experts in topics of current interest on May 29, and will be followed by a two-day conference featuring keynote addresses by internationally renowned statisticians, a student paper competition, a poster session and many stimulating invited talks. A banquet will be held on May 30, 2019 at Wyndham Hotel.

Downtown Pittsburgh

Please visit the official website of the LiDS 2019 Conference at lids2019.pitt.edu.

Quick Link:


Keynote Speakers

Odd O. Aalen (University of Oslo, Norway)
Causal Inference for Survival Data, with Emphasis on Mediation Analysis
Thursday, May 30, 2019, 9:00 am - 10:00 am

Ross Prentice (Fred Hutchinson Cancer Research Center; University of Washington)
Regression Models and Multivariate Life Tables
Friday, May 31, 2019, 8:00 am - 9:00 am

Danyu Lin (University of North Carolina at Chapel Hill)
Semiparametric Regression Analysis of Interval-Censored Data
Friday, May 31, 2019, 9:00 am - 10:00 am


Keynote Presentation I

Odd O. Aalen Causal Inference for Survival Data, with Emphasis on Mediation Analysis
Thursday, May 30, 2019, 9:00 am - 10:00 am

Odd O. Aalen
 (University of Oslo, Norway)


Causal inference is becoming an important theme in survival analysis. We discuss causal mediation analyses for survival data and propose an approach based on the additive hazards model. The emphasis is on a dynamic point of view, that is,understanding how the direct and indirect effects develop over time. To define direct and indirect effects in a longitudinal survival setting we take an interventional approach (Didelez, 2018) where treatment is separated into one aspect affecting the mediator and a different aspect affecting survival. In general, this leads to a version of the non-parametric g-formula (Robins, 1986). In the present talk, we demonstrate that combining the g-formula with the additive hazards model and a linear structural equation model for the mediator process results in simple and interpretable expressions for direct and indirect effects in terms of relative survival as well as cumulative hazards. Our results generalise and formalise the method of dynamic path analysis (Fosen et al, 2006; Strohmaier et al, 2015) and also work by Lange and Hansen (2011). An application will be given.



Keynote Presentation II

Ross Prentice Regression Models and Multivariate Life Tables
Friday, May 31, 2019, 8:00 am - 9:00 am

Ross Prentice (Fred Hutchinson Cancer Research Center; University of Washington)


Regression methods that adapt Cox regression to multivariate failure times, on the same or different failure time axes, will be presented. These methods specify Cox type semiparametric regression models for marginal single and double failure rates, and use estimating functions and empirical process methods, like those developed by Danyu Lin, L.J. Wei and colleagues for marginal single failure hazard rates, for hazard ratio parameter and for baseline hazard rate estimation. Sandwich type variance process estimators are developed for all model parameters, along with a perturbation resampling procedure for complex constructs of modeled parameters. As a byproduct semiparametric estimators of pairwise survivor functions, given covariates that may be evolving in time, are readily obtained from Peano series representations of these survivor functions in terms of marginal single and double failure rates, and corresponding semiparametric estimators of cross ratio and concordance functions are also readily obtained to characterize pairwise dependencies between failure times given covariates. An application to clinical outcome data from a large low-fat dietary intervention trial among postmenopausal women will be presented, and some contrast between these approaches and those based on counting process intensity modeling, as well as on frailty and copula modeling, will be provided. This is joint work with Dr. Shanshan Zhao of NIH/NIEHS.



Keynote Presentation III

Danyu Lin Semiparametric Regression Analysis of Interval-Censored Data
Friday, May 31, 2019, 9:00 am - 10:00 am

Danyu Lin (Department of Biostatistics, University of North Carolina at Chapel Hill)

Interval censoring arises frequently in clinical, epidemiological, financial, and sociological studies, where the event or failure of interest is not observed at an exact time point but is rather known to occur within a time interval induced by periodic monitoring. We formulate the effects of potentially time-dependent covariates on the interval-censored failure time through semiparametric regression models, such as the Cox proportional hazards model. We study nonparametric maximum likelihood estimation with an arbitrary number of monitoring times for each study subject. We develop an EM algorithm that involves very simple calculations and converges stably for any dataset, even in the presence of time-dependent covariates. We show that the estimators for the regression parameters are consistent, asymptotically normal, and asymptotically efficient with an easily estimated covariance matrix. In addition, we extend the EM algorithm and asymptotic theory to competing risks and multivariate failure time data. Finally, we demonstrate the desirable performance of the proposed numerical and inferential procedures through simulation studies and applications to real medical studies.



Short Courses

All workshops will be held on Wednesday, May 29, 2019 from 8:30 am to 4:30 pm.


Short Course I: Two-Phase Studies for Lifetime Data
Instructors: Ørnulf Borgan and Sven Ove Samuelsen (University of Oslo, Norway)

Short Course II: Dynamic Prediction in Survival Analysis
Instructor: Hein Putter (Leiden University Medical Centre, The Netherlands)

Short Course III: Biased Sampling, Left Truncation and Survival Analysis
Instructor: Jing Qin (NIH/NIAID)


Short Course I: Two-Phase Studies for Lifetime Data

Instructors


Ornulf Borgan Ørnulf Borgan is professor of Statistics at the University of Oslo. His main research interest has been statistical methods for survival and event history data, including nested case-control and case-cohort designs. He is co-author of two books on the use of counting processes and martingales in survival and event history analysis, and he is one of the editors of the recent Handbook of Statistical Methods for Case- Control Studies (CRC Press, 2018). Borgan has been editor of the Scandinavian Journal of Statistics, and he is a Fellow of the American Statistical Association and member of the Norwegian Academy of Science and Letters.
Sven Ove Samuelsen

Sven Ove Samuelsen is professor of Statistics at the University of Oslo. His main research interest has been statistical methods for survival and event history data, in particular case-cohort and nested case-control designs. He has been involved in planning and analyzing many case-control and other epidemiological studies. Samuelsen is on the editorial board of Lifetime Data Analysis.



Overview

In cohort studies, regression methods are commonly applied to assess the influence of risk factors and other covariates on mortality or morbidity; in particular Cox-regression is much used. Estimation in Cox's model is based on a partial likelihood that at each observed death or disease occurrence ("failure'') compares the covariate values of the failing individual to those of all individuals at risk. Thus Cox regression requires collection of covariate information for all individuals in the cohort, even when only a small fraction of them actually get diseased or die. This may be very expensive, or even logistically impossible. Further, when covariate measurements are based on biological material stored in biobanks, it will imply a waste of valuable material that one may want to save for future studies. Cohort sampling designs, where covariate information is collected for all failing individuals ("cases'"), but only for a sample of the individuals who do not fail ("controls'"), then offer useful alternatives that may save biological material and drastically reduce the workload of data collection and error checking. Such cohort sampling designs may be considered as two-phase designs, where the cohort is the phase I sample (selected from a superpopulation) and the case-control sample is the phase II sample selected from the cohort.

There are two main types of two-phase designs for life time data: nested case-control and case-cohort designs, and the two types of designs differ in the way controls are selected. The course presents the two types of designs both in their original form and later extensions and describes how the statistical analysis of such two-phase studies may be performed. The focus is on estimation of relative risks using partial likelihoods and pseudo-likelihoods (or weighted likelihoods) that resemble the full cohort partial likelihood. Other topics like estimation of absolute risk and model checking will also be discussed, and methods that use all available data in the full cohort will be mentioned. There will be practical exercises in analyzing two-phase life time data, and the participants should bring their own laptop with R installed. Information on R packages that are needed will be given closer to the course.

Aims

  1. Introduce the most common two-phase designs for life time data: nested case-control and case-cohort.
  2. Discuss classical statistical methods for estimating relative risks for two-phase life time data, and give an outline of their theoretical properties.
  3. Discuss methods for absolute risk estimation and model assessment.
  4. Describe two-phase methods that use all available data from the full cohort.
  5. Illustrate how to carry out statistical analyses of two-phase life time data using R.


Learning Outcomes

At the end of the day participants should:

  1. Know the characteristics of the two common types of two-phase designs for life time data and understand the pros and cons of the designs.
  2. Know how to estimate relative and absolute risks from nested case-control and case-cohort data.
  3. Have some knowledge of methods that make use of data that are available for the full cohort.
  4. Have some experience in analyzing nested case-control and case-cohort data using R.


Topics Covered

The material will be presented in a lecture format, where the theory and methods will be motivated and illustrated by examples from health research. In addition, the participants will get hands-on experience with the methods from practical exercises using R. Topics covered include:

  1. Summary of methods for analyzing cohort life time data.
  2. Nested case-control designs, including counter-matched sampling of the controls.
  3. Case-cohort designs, including stratified sampling of the subcohort.
  4. Classical methods for estimating relative and absolute risk from nested case-control and case-cohort data.
  5. Analysis of general models for nested case-control and case-cohort data using inverse probability weighting.
  6. Calibration of inverse probability weights for case-cohort data.
  7. Methods for two-phase data that use all available cohort information (multiple imputation and maximum likelihood).
  8. Practical examples and exercises using R.


Learning Strategy

The material will be presented using slides, class discussion, and practical exercises using R. Attendees will be given a booklet containing the slides, which will contain clear descriptions of the methodology, of applications, and of how to implement analyses in R.


Prerequisites

The short course will be directed at statisticians in academia, government or industry interested in learning about two phase designs for life time data. It will be assumed that the participants are familiar with the basic concepts and methods in survival analysis and that they have some experience in using the R software.


Recommended Reading

  • Chapters 7 and 8 of Keogh & Cox: Case-Control Studies, Cambridge University Press, 2014.
  • Part IV of Handbook of Statistical Methods for Case-Control Studies, eds Borgan, Breslow, Chatterjee, Gail, Scott & Wild, CRC Press, 2018.


Short Course II: Dynamic Prediction in Survival Analysis


Instructor

Hein Putter

Hein Putter is Professor at the Leiden University Medical Center (Department of Biomedical Data Sciences). His research interests include competing risks and multi-state models, frailty models and dynamic prediction. He is co-author of the book “Dynamic Prediction in Clinical Survival Analysis”, with Hans van Houwelingen.



Overview


The medical literature abounds with prediction models. They are statistical models based on patient- and disease characteristics, used to inform treatment decisions, to provide personalized risk estimates for the patient, and also to stratify patients in clinical trials. Important prognostic models include Adjuvant! Online in cancer and the Framingham risk score in cardiovascular disease. The vast majority of these models are focused on prognosis at one well-defined baseline moment, typically at diagnosis, shortly before treatment is initiated. It is at this time that the most important decisions on primary treatment are made. There is little doubt that the available prognostic models are important tools for the treating physician to guide treatment decisions at diagnosis. However, once primary treatment has been initiated, the prognosis of the patient will change over the course of time, as a result of the effect of treatment, possible treatment toxicity, and clinical events such as disease recurrence that may have occurred, and, very simply, because of the fact that the patient is still alive. As a result, these prediction models need to be “updated” to use the knowledge that has become available since baseline. Prediction models that incorporate this dynamic aspect are called dynamic prediction models, and they are the topic of this course.


This course will focus on methodology for dynamic prediction. The dynamic aspect of dynamic prediction involves using information on events and/or measurements up to the present, in order to “update” the prediction. It will be shown in this course how dynamic predictions may be obtained using the concept of landmarking and using multi-state models. Analyses will be illustrated using R, in particular the mstate and dynpred packages. Implementation of the methods in other statistical software packages like SAS, Stata and SPSS will be discussed.

Aims

  1. Discuss situations where dynamic prediction is relevant;
  2. Illustrate how the Cox model can be used to obtain dynamic predictions with time-fixed covariates;
  3. Introduce multi-state models as an extension of survival analysis and competing risks;
  4. Show how multi-state models can be used to obtain dynamic predictions;
  5. Introduce landmarking as a way of dealing with time-dependent covariates;
  6. Show how landmarking can be used to include time-dependent information in the dynamic predictions;
  7. Discuss robustness properties;
  8. Illustrate how to carry out the analyses discussed during the course using R.


Learning Outcomes


At the end of the course participants should:

  1. Understand the connection between hazards and dynamic prediction probabilities;
  2. Know how to obtain dynamic prediction probabilities from time-fixed Cox models;
  3. Understand the difficulties of predicting with time-dependent covariates;
  4. Be acquainted with concepts in multi-state models like transition intensities, transition probabilities, state occupation probabilities, the Markov assumption;
  5. Understand the relation between transition intensities and transition probabilities, and be acquainted with the Aalen-Johansen estimator;
  6. Understand how landmarking can be used for dynamic prediction

Topics Covered


The course material will be presented in a lecture format, changing between theory and illustrations. Ample attention will be devoted to the practical implementation of the methods covered in the course, using R.


Topics covered include:
  • Dynamic use of familiar survival analysis techniques: A short overview of survival analysis will be given, including the Cox model. The emphasis in this overview will be on how these familiar techniques can be used to obtain dynamic predictions. We will introduce conditional survival (the effect of being alive) and the fixed width failure function, and their relation to the familiar hazard function. Extensions to competing risks will briefly be mentioned.
  • Time-dependent covariates and landmarking: We will then introduce time-dependent covariates and discuss techniques to handle them such as time-dependent Cox regression and landmarking. The differences between these approaches and the relative merits will be discussed.
  • Multi-state models: A brief overview of multi-state models will be given, including how they can be used to obtain dynamic predictions. The overview includes discussion of concepts like transition intensities and transition probabilities, and ways of estimating transition intensities. The Aalen-Johansen estimator of the transition probabilities will be presented, and the assumptions needed for validity of the Aalen-Johansen estimator, in particular the Markov assumption will be discussed.
  • Landmarking and dynamic prediction: Then we will show how landmarking can be used to include time-dependent information in the dynamic predictions. We will briefly discuss more traditional methods that can also be used for dynamic prediction, such as multi-state models. Advantages and disadvantages of different approaches will be discussed.
  • Practical implementation: Methods discussed during the lectures will be illustrated using R, and in particular the mstate and dynpred packages. Data used is available from the presenter upon request.

Learning Strategy


The material will be presented using slides and through class discussion. Attendees will be given a booklet containing the slides, which will contain clear descriptions of the methodology, of applications, and of how to implement analyses in R.



Prerequisites


This course is directed at statisticians or epidemiologists in academia, government or industry interested in dynamic prediction in survival analysis. Participants are expected to have a fair knowledge of the techniques from classical survival analysis.



Short Course III: Biased Sampling, Left Truncation and Survival Analysis

Instructor

Jing Qin

Jing Qin is a Mathematical Statistician at the Biostatistics Research Branch in the National Institute of Allergy and Infectious Diseases. Dr. Qin’s research interests include empirical likelihood method, case-control study, length bias sampling, econometrics, survival analysis, missing data, causal inference, genetic mixture models, generalized linear models, survey sampling and microarray data analysis. He is the author of “Biased sampling, over-identied parametric problems and beyond” (Springer, 2017). He was elected as a Fellow of the American Statistical Association in 2006.



Overview


Biased sampling occurs when a proper randomization cannot be achieved, the observed sample will not be representative of the population of interest. Biased sampling problems appear in many areas of research, including, Medicine, Epidemiology and Public Health, Social Sciences and Economics. Left truncation and length-biased data are clearly encountered in applications of renewal processes, etiologic studies, genome-wide linkage studies, epidemiologic cohort studies, cancer prevention trials, and studies of labor economy. In observational studies, a prevalent cohort design that draws samples from individuals with a condition or disease at the time of enrollment is generally more efficient and practical. The recruited patients who have already experienced an initiating event are followed prospectively for the failure event (e.g. disease progression or death) or are right censored. Under this sampling design, individuals with longer survival times measured from the onset of the disease are more likely to be included in the cohort, whereas those with shorter survival times are unconsciously excluded. Finding appropriate adjustments for the potential selection bias in analyzing length-biased data or more general biased sampling problems has been a long standing statistical problem.

This workshop discusses various methods to deal with biased sampling problems, exponential tilting models and left truncation and right censored data problems, including prole maximum likelihood method, conditioning likelihood method, composite partial likelihood method as well as general imputation methods.

Aims and Topics Covered

  1. Discuss the general methods for handling biased sampling problems, including case and control problems, missing data and casual inference.
  2. Derive the Cox partial likelihood from different angles, including rank likelihood method, prole maximum likelihood method, case and control conditional likelihood argument, and optimal estimating equation method.
  3. Present the latest results on analyzing length biased survival time data, including Vardi’s multiplicative censoring problem, and general imputation principle for missing survival data.
  4. Discuss the well known pool adjacent violators algorithm and its combination with the EM algorithm together for estimating shape constrained inference, including estimation of monotonic decreasing density, cumulation hazard or distribution function based on current status data etc.


Learning Outcomes

At the end of the day participants should have some new ideas on handling biased sampling problems and survival data. This course is particularly helpful for those who are interested in learning some “theoretical results” and some “applied problems”. The accompanied R programs will be discussed.



Invited Sessions and Speakers

Download Final Program Schedule


Multi-State Models in Practice
Organizer
Mouna Akacha
David James, 
Multistate Modeling and Simulation of Patient Trajectories After Allogeneic Hematopoietic Stem Cell Transplantation to Inform Drug Development
Ulrich Beyer, 
A Multistate Model for Early Decision Making in Oncology
Jan Feifel, 
Utilization of Multistate Models and Subcohorting to Analyze Rare Exposures
Terry Therneau,
 Practical Multi-State Models

Innovative Approaches for Studying the Effects of Chemical Mixtures on Disease Throughout the Life-span

Organizer: Paul Albert
Shelley Liu, Bayesian Methods for Analyzing Chemical Mixtures

David Wheeler, Association of Early-life Exposure to Tobacco Metabolites and Other Non-organic Metals and Behavioral Symptoms of Attention Deficit Hyperactivity Disorder
Zhen Chen, A Bayesian Multi-dimensional Couple-based Latent Risk Model with an Application to Infertility

Methods for Dependent Truncation
Organizer: Rebecca A. Betensky
Lior Rennert, Cox Regression Model under Dependent Truncation

Jing Qian, Estimation of the Survival Distribution under Covariate-Induced Dependent Truncation using Inverse Probability of Weighting
Bella Vakulenko-Lagun, Nonidentifiability in the Presence of Factorization for Truncated Data

Clinical Trial Design and Data Analysis with Late-Onset Effects
Organizers: Chunyan Cai and Yongseok Park
Chunyan Cai, A Bayesian Design for Phase II Clinical Trials with Late-onset Responses Based on Multiple Imputation
Ying Yuan
, Time-to-Event Bayesian Optimal Phase II Trial Design for Cancer Immunotherapy

Mengling Liu, Design and Analysis of Clinical Trials in the Presence of Delayed Treatment Effect
Yongseok Park, Designing Cancer Immunotherapy Trials with Random Treatment Time-Lag Effect

Advanced Statistical Methods for Time to Event Data in Complex Observational Studies
Organizer: Jianwen Cai
Haibo Zhou, Secondary Analysis in Outcome Dependent Sampling Studies

Yu Shen, Density Ratio Model for Analyzing Length-Biased Data
Qingning Zhou, Outcome-Auxiliary-Dependent Sampling with Failure Time Data
Donglin Zeng, Semiparametric Regression Analysis of Multiple Right- and Interval-Censored Events

Recent Development of Bayesian Joint Modeling of Time-to-Event and Longitudinal or Spatial Data
Organizer: Ming-Hui Chen

Paul Albert, A Joint Model Approach for Longitudinal Data with no Time-Zero and Time-To-Event with Competing Risks
Guanyu Hu, Bayesian Variable Selection for Cox Regression Model with Spatially Varying Coefficients with Applications
Ming-Hui Chen, Assessing Importance of Biomarkers: a Bayesian Joint Modeling Approach of Longitudinal and Survival Data with Semicompeting Risks

Advanced Analysis Methods for Survival Outcome with High-Dimensional Data
Organizer: Wei Chen
Heng Huang, Deep Learning for Biomedical Data Analysis

Yanming Li, XG Boosting Variable Selection for a Discrete Time Cure Rate Survival Model with High-Dimensional Time Varying Imaging Predictors
Jialiang Li, Multi-threshold Accelerated Failure Time Model
Ying Ding, A Copula-Based Semiparametric Model for Progression Prediction of Age-Related Macular Degeneration (AMD) using GWAS Data

Novel Semi-parametric Models for Complex Survival Data
Organizer: Yu Cheng

Jing Ning, Semiparametric Model and Inference for Bivariate Survival Data Subject to Biased Sampling
Sunyoung Shin, Ensemble Estimation and Variable Selection with Semiparametric Regression Models
Xianghua Luo, Time-dependent Covariates in Recurrent Event Models
Thomas Scheike, Excess Risk in the Matched Cohort Study

Founders Session on Current Topics in Lifetime Data Analysis
Organizer: Richard Cook

Mei-Ling Ting Lee, Distribution-free Threshold Regression for Longitudinal Time-to-event Analysis
Jack Kalbfleisch, Direct and Indirect Standardized Mortality Ratios Based on the Cox Model
Mei-Cheng Wang, Complexity in Simple Cross-Sectional Data with Binary Disease Outcome

Methods for Lifetime Data Processes Under Intermittent Observation
Organizer: Richard Cook

Jerald Lawless, Independence Conditions and Life History Analysis with Intermittent Observation of Individuals
Pamela Shaw, Assessing Efficacy for an Interval-censored Bivariate Failure Time Outcome When One Event is a Surrogate
Andrew Titman, A Joint Models for Multi-state Models with Informative Observation Processes

Advances in the Analysis of Composite Endpoints subject to Component-wise Censoring
Organizer: Guoqing Diao

Junshan Qiu, The Stratified Win Ratio
Audrey Boruvka, Computation and Applications in Joint Models for Progression and Survival under Componentwise Censoring
Guoqing Diao, Semiparametric Regression Analysis for Composite Endpoints Subject to Component-Wise Censoring

Invited Session for Student Conference Award Winners (1)
Organizer: Guoqing Diao
Ting Ye, Robust Tests for Treatment Effect in Survival Analysis under Covariate-Adaptive Randomization
Gabrielle Simoneau, Estimating Optimal Dynamic Treatment Regimes with Survival Outcomes
Rui Chen, Tailored Optimal Post-Treatment Surveillance for Cancer Recurrence
Nicole Butera, Estimating Biomarker Change by Adjusting for Informative Time to Treatment Initiation

Invited Session for Student Conference Award Winners (2)
Organizer: Guoqing Diao
Bo Wei, Generalized Accelerated Recurrence Time Model in the Presence of a Dependent Terminal Event
Zhixing Xu, A Latent Class Based Joint Model for Recurrence and Termination: A Bayesian Recourse
Yi Xiong, Estimating Duration Distribution from Data with Missing Time Origin
Yue Wei, Gene-based Association Analysis for Bivariate Time-to-event Data Through Functional Regression with Copula Models

Recent Advances in Complex Bivariate Time-to-Event Data Modeling and Analysis
Organizer: Ying Ding
Yu Cheng, Quantile Association Model for Bivariate Survival Data

Joanna Shih, Analysis of Competing Risk Data with Reporting Error in Age at Onset and Misclassified Failure Type
Jong Hyeon Jeong, A Clustered Win Ratio for Semi-Competing Risks Data

Complex Data Analysis in the Biomedical and Health Research
Organizer: Ruzong Fan
Christopher I. Amos, Understanding Complex Etiology of Autoimmune Diseases by Application of Machine Learning Tools

Jason H. Moore, Accessible Artificial Intelligence for Data Science
Saonli Basu, A Robust and Unified Framework for Estimating Heritability in Twin Studies using Generalized Estimating Equations
Ruzong Fan, Mixed Models for Gene-based Association Analysis of Complex Traits

Causal Inference in Life History Analysis
Organizer: Jon Michael Gran
Kjetil Røysland, Causal Interpretation in Survival Analysis

Mats Julius Stensrud, New Estimands for Causal Inference in the Presence of Competing Risks
Ruth Keogh, The Sequential Trials Approach for Estimating Effects of Treatment on Survival Using Longitudinal Observational Data

Cross-Sectional Analysis of Life History Data
Organizer: X. Joan Hu
Leilei Zeng, Multistate Analysis from Cross-Sectional and Auxiliary Samples
Niels Keiding, Possible Application of Current Duration Analysis to Estimate Time-to-Pregnancy Distributions from Demographic Survey Data
Cuiling Wang, Evaluate Cross-Sectional Association and Diagnostic Accuracy for Disease using Longitudinal Markers with Missing Data

Recent Advances in Survival and Recurrent Event Data Analysis
Organizer: Chiung-Yu Huang
Lili Wang, Penalized Survival Models for the Analysis of Alternating Recurrent Event Data

Yifei Sun, Recurrent Event Trees and Forests
Zhezhen Jin, On Competing Risk Analysis of Kidney Transplant Data
Mi-Ok Kim, Causal Inference of Time to Event Outcome with Random Forest

Survival Analysis Methods for Complex Sample Data
Organizer: Noorie Hyun

Takumi Saegusa, Survival Analysis for Integrated Data from Multiple Sources
Soyoung Kim, Subdistribution Hazards Model for Case-Cohort Studies
Noorie Hyun, Sample-Weighted Semiparametric Models for Competing Risks Data Subject to Left-/Interval Censoring from Electronic Health Records
Ai (Andy) Ni, Concordance Measures in Survival Analysis on Survey Data

Joint Models for Time-to-Event and Multiple Longitudinal Data OR High Dimensional Data
Organizer: Helene Jacqmin-Gadda
Sheng Luo, Dynamic Prediction of Alzheimer’s Disease Progression Using Features of Multiple Longitudinal Outcomes and Time-to-Event Data

Cecile Proust-Lima, Joint Modelling of Multiple Latent Processes and Clinical Endpoints: Application in Alzheimers Disease
Dimitris Rizopoulos, Using Joint Models for Personalized Optimal Scheduling of Invasive Procedures

Recent Developments in Statistical Methods on Semi-Competing Risks Data
Organizer: Jong Hyeon Jeong

David Oakes, Nonparametric Estimation of the Curtailed Win-Ratio
Lu Mao, On the Win-Loss Processes of Composite Endpoints
Il-Do Ha, H-likelihood Approaches for Frailty Models with Semi-competing Risks Data

Novel Approaches for Time-to-Event Data
Organizer: Aiyi Liu

Wei Qian, Double-slicing Assisted Sufficient Dimension Reduction for High Dimensional Censored Data
Rajeshwari Sundaram, Joint Modeling of First Stage and Second Stage of Labor in Pregnant Women
Antai Wang, Analysis of Semi-competing Risks Data using Archimedean Copula Models

Survival Analysis Methods for Alzheimer’s Disease
Organizer: Lei Liu
Richard Chappell, Bent Lines and Quantiles

Sharon X. Xie, Adjusting for Covariate Measurement Error in Failure Time Analysis Under Competing Risks with Applications to Alzheimers Disease Biomarker Research
Guoqiao Wang, Survival Analysis for Alzheimer Disease Without "Known Survival" Time
Dandan Liu, Partly Conditional Modeling for Alzheimers Disease Progression

Causal Inference with Time-to-Event Data
Organizer: Lu Mao

Mark van der Laan, Target MLE and Survival Analysis
Yifan Cui, Instrumental Variable Estimation of Marginal Structural Cox Model for Time-Varying Exposure
Constantine Frangakis, Deductive Semiparametric Estimation in Double-Sampling Designs with Application to Estimating Mortality in PEPFAR

Causal Conclusions Based on Cox Regression Analysis
Organizer: Torben Martinussen

Jonathan Bartlett, Hazard Ratios - What’s Different and What’s Not
Morten Valberg, Potential Causal Consequences of Observed Proportional Hazards
Torben Martinussen, Subtleties in the Interpretation of Hazard Ratios

Survival Analysis with Missing or Mismeasured Data
Organizer: Bin Nan

Ronghui (Lily) Xu, Two-Stage Residual Inclusion for Survival Data and Competing Risks - An Instrumental Variable Approach for Binary Treatment with Application to SEER-Medicare Linked Data
Grace Y. Yi, Semiparametric Methods for Left-truncated and Right-censored Survival Data with Covariate Measurement Error
Yichuan Zhao, Rank-based Estimating Equation with Non-ignorable Missing Responses

Survival Analysis with Error-Prone or Missing Covariate Measurements
Organizer: Daniel Nevo
Daniel Nevo, A Novel Calibration Framework for Survival Analysis When a Binary Covariate is Measured at Sparse Time Points

Xiao Song, Partially Time-Varying Coefficient Proportional Hazards Models with Error-Prone Time-Dependent Covariates -an Application to the AIDS Clinical Trial Group 175 Data
Molin Wang, Survival Analysis with Functions of Mismeasured Covariate Histories

Threshold Modeling, Cancer Risk, and Agreement Assessments
Organizer: Edsel A. Pena

Michael Pennell, A Bayesian Semiparametric First Hitting Time Model for Latent Fetal Development
Jungin Kim, Accounting for Preinvasive Conditions in the Analysis of Invasive Cancer Risk: With Application to Breast Cancer and the Sister Study
Fazlur Rahman, Nonparametric Regression Method for Broad Sense Agreement

Multiple Testing, Simultaneous and Joint Modeling, and Calibration
Organizer: Edsel A. Pena

Yen-Yi Ho, P-value Adjustment Procedure Using Empirical Weights
Piaomu Liu, Joint Dynamic Modeling of a Longitudinal Marker, Recurrent Competing Risks and a Terminal Event
Beidi Qiang, Estimating Concentration Response Function and Change-Point using Time-Course and Calibration Data

Mediation Analysis for High-Dimensional Data
Organizer: Ruth Pfeiffer
Joshua Millstein, Challenges of Mediation Analysis in Genomic Settings in the Presence of Reverse Causality

Michael B. Sohn, A Compositional Mediation Model for Microbiome Data
Andriy Derkach, High Dimensional Mediation Analysis with Latent Variables
Xi Luo, Mediation Analysis for Large and Multilevel Data

Multistate Models as A Framework for Life History Analysis
Organizer: Hein Putter

Hans C. van Houwelingen, An Alternative for the Fine-Gray Approach to Competing Risk Modelling: a Bridge Between Multi-State and Subdistribution Hazard
Ronald Geskus, A Bayesian Analysis of the Natural History of HIV-2 Infection using a Hidden Markov Cure Model
Jeremy Taylor, Handling Missing Covariate Data in Multistate Models
Jon Michael Gran, Estimating Causal Effects of Time-varying Treatments in Multi-State Models - An Application to Registry Data on Sick Leave and Disability

Novel Methods for the Analysis of Recurrent Event Data
Organizer: Douglas Schaubel
Jianwen Cai, Analysis of Recurrent Events Data from Case-Cohort Studies

Chiung-Yu Huang, Generalized Proportional Rate Models for Recurrent Event Data
Sehee Kim, C-index for Multiple Type Recurrent Event Data

Models and Applications with Recurrent Events
Organizer: Thomas Scheike
Virginie Rondeau, Multivariate Joint Frailty Model for the Analysis of Nonlinear Tumor Kinetics with Recurrent Progressions of Nontarget Progression and Dynamic Predictions of Death
Per Kragh Andersen, Marginal Regression Models for Recurrent Events with Competing Risks using Pseudo-Obervations
Frank Eriksson, The Mean, Variance, and Correlation for Bivariate Recurrent Events Data with a Terminal Event

Recent Advances in the Analysis of Complex Lifetime Data Involving Recurrent Events
Organizer: Hua Shen

Ming Wang, A Time-varying Joint Frailty-copula Model for Analyzing Recurrent Events and a Terminal Event: An Application to the Cardiovascular Health Study
Kaida Cai, Bi-level Variable Selection for Multivariate Failure Time Data with Observed Heterogeneity
Shu Jiang, Finite Mixture Models for Multistate Processes under Panel Observation

Challenges and Advances of Research in Health Service Studies
Organizer: Yu Shen

Jane Lange, How Should we Handle Medical Data with Surveillance-Dependent Outcomes?
Nabihah Tayob, Longitudinal Biomarker Screening Algorithms: Guidelines for When They are Most Useful
Liang Li, Modeling Caners Cost Trajectory with the Terminal Event

Estimands: The First Update to Regulatory Statistical Guidance in 20 Years - The Pharmaceutical Industry Working Group on Estimands in Oncology
Organizer: Jonathan Siegel

Jonathan Siegel, Survival Trial Design Strategies in an Estimands Framework
Feng Liu, Developing Estimands in Oncology Trials
Shoubhik Mondal, Sensitivity Analyses in Estimands in Oncology

Personalized Treatment Selection with Censored Survival Outcome
Organizer: Xiao Song

Abdus S. Wahed, Optimizing Dynamic Treatment Regimes Based on Quality-Adjusted Survival
Yingqi Zhao, Personalized Adjusted Benefit on Measuring Treatment Effects
Lihui Zhao, Dynamic Prediction Methods for Personalized Cardiovascular Disease Prevention and Treatment

Recent Development in the Analysis of Recurrent Event Data
Organizer: Jianguo (Tony) Sun

Yang Li, A General Additive-Multiplicative Mean Model for Panel Count Data Analysis
Liang Zhu, Statistical Analysis on Mixed Recurrent Event Data with Clusters
Shijun Zhu, A Joint Model of Longitudinal Biomarkers and Recurrent Events and It's Application

Innovative Applications of Joint Modeling
Organizer: Rajeshwari Sundaram
Qing Pan, Joint Modeling of Adenoma Recurrences and Cancer Risks Using Panel Count Data with Informative Screening Times

Sedigheh Mirzaei, Statistical Modeling of Discrete Survival Time in Presence of Recall Bias: A Joint Modeling Approach
Youjin Lee, Joint Modeling Competing Risks Data and Current Status Data: With Application to Spontaneous Labor
Li Cheung, Mixture Models for Undiagnosed Prevalent Disease and Interval Censored Incident Disease: Applications to a Cohort Assembled from Electronic Health Records

Innovative Methods for Assessing Diagnostic Accuracy and Prediction Accuracy
Organizer: Rajeshwari Sundaram

Paramita Saha-Chaudhuri, Monitoring with Repeatedly Measured Marker: Assessing Incremental Value of Additional Measurements
Aasthaa Bansal, Evaluating the Time-varying Prediction Accuracy of Survival Models Used in Dynamic Decision-making
Hormuzd Katki, Mean Risk Stratification and Number Needed to Test: A New Approach to Quantifying Risk Stratification for Comparing the Usefulness of Diagnostic Tests

Invited Session on Biostatistics Methods
Organizer: Mei-Ling Ting Lee
Chung-Chou H. (Joyce) Chang, Modeling Exposure-Time-Response Association in the Presence of Competing Risks

Catherine Huber, Epidemiology of Primary Immunity Deficiency using Regression Models for Right Truncated Data
Ying Qing Chen, Data Enriched Regression for Censored Time-to-Event
Jonathan Race, Semiparametric Bayes Testing of Ordinal Effects on Survival

Invited Session on Applied Stochastic Models for Time-to-Event Data
Organizer: Mei-Ling Ting Lee
Satish Iyengar, Diffusion Models for Time-to-Event Data

Chien-Yu Peng, Robust Processes in Degradation Analysis
Tianzhou Ma, Variable Screening with Multiple Studies

Invited Session on Genomic Applications
Organizer: Mei-Ling Ting Lee
George Tseng, Robust Machine Learning Method for Predicting Survival using Genomic Data

Philippe Broet, Predicting the Occurrence of an Adverse Event using Bagged Survival Trees Built on Random Structured Subsets: Application in Clinical Immunology
Chien-Wei Lin, RNASeqDesign: A Framework for RNA-Seq Genome-wide Power Calculation and Study Design Issues

Extensions to Joint Longitudinal-Survival Modelling
Organizer: Andrew Titman

Li Su, Accommodating Informative Dropout and Death: A Joint Modelling Approach for Longitudinal and Semicompeting Risks Data
Zhigang Li, Joint Modeling Quality of Life and Survival in Palliative Care Research
Michael Crowther, Extended Multivariate Generalised Linear and Non-linear Mixed Effects Models

New Methods for Risk Prediction and Precision Medicine
Organizer: Mei-Cheng Wang
Yanxun Xu, Bayesian estimation of Individualized Treatment-Response Curves in Electronic Medical Record Data

Jon Steingrimsson, Deep Learning with Time-to-event Outcomes
Xingqiu Zhao, Subgroup Analysis for Cox Regression

Prediction and Estimation for Complex Survival Data
Organizer: Ronghui (Lily) Xu

Yingwei (Paul) Peng, Measures of Explained Variation under the Cure Model for Survival Data
Wenqing He, Parametric and Semiparametric Estimation Methods for Survival Data under a Flexible Class of Models
Yuan Wu, Predictive Accuracy of Markers or Risk Scores for Interval Censored Survival Data

Causal Inference for Survival Data
Organizer: Ronghui (Lily) Xu

Jelena Bradic, Inference on Treatment Effects in High-dimensional Survival Models
Eric J. Tchetgen Tchetgen, Mendelian Randomization for Failure Time Outcome with Invalid Instrumental Variables
Jessica Young, The Choice to Define Competing Risk Events as Censoring Events and Implications for Causal Inference

Emerging Issues and Methods on Censored Data
Organizer: Grace Y. Yi
Masoud Asgharian, Prevalent Cohort Studies: Length-Biased Sampling with Right Censoring

Douglas Schaubel, Semiparametric Regression Methods for Temporal Processes Subject to Multiple Sources of Censoring
Gang Li, Ultrahigh Dimensional Screening for Survival Data

Novel Application of Survival Models in Complex Biomedical Studies
Organizer: Donglin Zeng

Yuanjia Wang, Early Diagnosis of Neurological Disease Using Peak Degeneration Ages of Multiple Biomarkers
Fei Gao, Semiparametric Regression Analysis of Length-Biased Interval-Censored Data
Qingxia Chen, Treatment Effect Estimate and Model Diagnostics with Two-way Time-Varying Treatment Switching: An Application to a Head and Neck Study

Intermittent Observation of Life History Processes
Organizer: Leilei Zeng
X. Joan Hu, Left Censoring/Truncation Involved in Administrative Data Analysis
Yueh-Ying Han, Utilizing National Health Survey Data for Surviving Analysis
Eleanor Pullenayegum, The Role of Recurrent Event Models in the Analysis of Longitudinal Data Subject to Irregular Observation: Current Practice and Future Directions



Scientific Program Committee

Richard Cook
(Co-Chair, University of Waterloo)
Jianwen Cai (Co-Chair, University of North Carolina at Chapel Hill)


Other Program Committees include

Mouna Akacha (Novartis, Switzerland)
Paul Albert (NIH/NCI)
Rebecca A. Betensky (Havard University)
Chunyan Cai (University of Texas Health Science Center at Houston)
Ming-Hui Chen (University of Connecticut)
Wei Chen (University of Pittsburgh School of Medicine)
Yu Cheng (University of Pittsburgh)
Guoqing Diao (George Mason University)
Ying Ding (Univeristy of Pittsburgh)
Ruzong Fan (Georgetown University Medical Center)
Jon Michael Gran (University of Oslo, Norway)
Joan Hu (Simon Fraser University, Canada)
Chiung-Yu Huang (University of California, San Francisco)
Noorie Hyun (Medical College of Wisconsin)
Helene Jacqmin-Gadda (Universite de Bordeaux, France)
Jong Hyeon Jeong (University of Pittsburgh)
Nicholas Jewell (London School of Hygiene & Tropical Medicine, U.K.)
Jack Kalbfleisch (University of Michigan)
Aiyi Liu (NIH/NICHD)
Lei Liu (Washington University in St. Louis)
Lu Mao (University of Wisconsin-Madison)
Torben Martinussen (University of Copenhagen, Denmark)
Bin Nan (University of Michigan)
Daniel Nevo (Tel Aviv University, Israel)
Yongseok Park (University of Pittsburgh)
Edsel A. Pena (University of South Carolina)
Ruth Pfeiffer (NIH/NCI)
Hein Putter (Leiden University Medical Centre, The Netherlands)
Douglas Schaubel (University of Michigan)
Thomas Scheike (University of Copenhagen, Denmark)
Jonathan Siegel (Bayer)
Hua Shen (University of Calgary, Canada)
Yu Shen (University of Texas MD Anderson Cancer Center)
Xiao Song (University of Georgia)
Jianguo (Tony) Sun (University of Missouri)
Rajeshwari Sundaram (NIH/NICHD)
Mei-Ling Ting Lee (University of Maryland, College Park)
Andrew Titman (Lancaster University, UK)
Mei-Cheng Wang (Johns Hopkins University)
Ronghui (Lily) Xu (University of California, San Diego)
Grace Y. Yi (University of Waterloo, Canada)
Donglin Zeng (University of North Carolina at Chapel Hill)
Leilei Zeng (University of Waterloo, Canada)



Organizing Committee at the University of Pittsburgh


Ying Ding (Co-Chair)
Yu Cheng (Co-Chair)
Wei Chen 
Jong Hyeon Jeong
Joyce Chang