Selected Publications
(by topic)
(See my CV or Google Scholar for a full list of publications.)
Statistical methods for developing adaptive digital interventions
Summary. My work in this area focuses on the development of flexible statistical and causal models to make sense of complex longitudinal data. This includes models for assessing time-varying effect of an intervention, identifying effect modification, and characterizing treatment effect heterogeneity across individuals. My research tackles complexity in longitudinal data in terms of high-dimensionality, endogeneity, and the mixed types of data collected. This work will advance scientific discoveries and aid intervention development and evaluation to promote health.
Statistical Methodology
Efficient and Globally Robust Causal Excursion Effect Estimation
Cheng, Z., Bell, L., & Qian, T.
[arXiv]Incorporating nonparametric methods for estimating causal excursion effects in mobile health with zero-inflated count outcomes
Liu, X., Qian, T., Bell, L., & Chakraborty, B.
[arXiv]Estimating Causal Effects for Binary Outcomes Using Per-Decision Inverse Probability Weighting
Bao, Y., Bell, L., Williamson, E., Garnett, C., & Qian, T
[arXiv]
ASA LiDS (Lifetime Data Science) Student Paper Honorable MentionSample Size Considerations for Micro-Randomized Trials with Binary Outcome
Eric Cohn, Tianchen Qian, Lauren Bell, Claire Garnett, Olga Perski, Susan Murphy
Statistics in Medicine, 2023
[journal] [github]The Micro-Randomized Trial for Developing Digital Interventions: Experimental Design and Data Analysis Considerations
Tianchen Qian, Ashley E. Walton, Linda M. Collins, Predrag Klasnja, Stephanie T. Lanza, Inbal Nahum-Shani, Mashifiqui Rabbi, Michael A. Russell, Maureen A. Walton, Hyesun Yoo, Susan Murphy
Psychological Methods, 2022
[journal] [arXiv]Estimating Time-Varying Causal Excursion Effect in Mobile Health with Binary Outcomes (with discussion)
Tianchen Qian, Hyesun Yoo, Predrag Klasnja, Daniel Almirall, Susan A. Murphy
Biometrika, 2020
[journal] [arXiv] [github] [rejoinder]Linear Mixed Models with Endogenous Covariates: Modeling Sequential Treatment Effects with Application to a Mobile Health Study (with discussion)
Tianchen Qian, Predrag Klasnja, Susan A. Murphy
Statistical Science, 2020
[journal] [arXiv] [github] [rejoinder]
Applications
How Notifications Affect Engagement With a Behavior Change App: Results From a Micro-Randomized Trial
Bell, L., Garnett, C., Bao, Y., Cheng, Z., Qian, T., Perski, O., Potts, H.W. and Williamson, E.
JMIR mHealth and uHealth, 2023
[journal]Sense2Stop: A micro-randomized trial using wearable sensors to optimize a just-in-time-adaptive stress management intervention for smoking relapse prevention
Samuel L. Battalio, David E. Conroy, Walter Dempsey, Peng Liao, Marianne Menictas, Susan Murphy, Inbal Nahum-Shani, Tianchen Qian, Santosh Kumar, Bonnie Spring
Contemporary Clinical Trials, 2021
[journal]Engagement with a behavior change app for alcohol reduction: Data visualization for longitudinal observational study
Lauren Bell, Claire Garnett, Tianchen Qian, Olga Perski, Elizabeth Williamson, Henry Potts
Journal of Medical Internet Research (JMIR), 2020
[journal]Notifications to improve engagement with an alcohol reduction app: Protocol for a micro-randomized trial
Lauren Bell, Claire Garnett, Tianchen Qian, Olga Perski, Henry Potts, Elizabeth Williamson
JMIR Research Protocols, 2020
[journal]
Semiparametric models for causal inference and missing data
Summary. I develop computational methods for semiparametric models. These methods produce semiparametric estimators (with desired robustness properties) without the difficult case-by-case derivation of the efficient influence function (EIF) that is required by conventional semiparametric methods. This work will broaden the applicability of semiparametric models and robust estimators and give rise to new solutions to a variety of causal inference and missing data problems.
Deductive Semiparametric Estimation in Double-Sampling Designs with Application to PEPFAR
Tianchen Qian, Constantine Frangakis, Constantin Yiannoutsos
Statistics in Biosciences, 2019
[journal] [arXiv] [github]Deductive Derivation and Turing-Computerization of Semiparametric Efficient Estimation (with discussion)
Constantine Frangakis, Tianchen Qian, Zhenke Wu, Ivan Diaz
Biometrics, 2015
[journal] [github] [rejoinder]
Design and analysis of clinical trials and adaptive trials
Summary. I work on the design and analysis of clinical trials. On the design front, I work on adaptive enrichment designs (where at an interim analysis the trial enrollment is "enriched" to focus on certain subpopulation) and multiple testing procedure for such designs. On the analysis front, I work on (mostly semiparametric) estimators that adjust for baseline variables and short-term outcomes for group sequential designs.
Improving Power in Group Sequential, Randomized Trials by Adjusting for Prognostic Baseline Variables and Short-term Outcomes
Tianchen Qian, Michael Rosenblum, Huitong Qiu
Under review
[arXiv] [github]Comparison of Adaptive Randomized Trial Designs for Time-to-event Outcomes That Expand Versus Restrict Enrollment Criteria, to Test Non-inferiority
Joshua Betz, Jon Arni Steingrimsson, Tianchen Qian, Michael Rosenblum
Under review
[bepress]Optimized Adaptive Enrichment Designs for Multi-arm Trials: Learning Which Subpopulations Benefit from Different Treatments
Jon Arni Steingrimsson, Joshua Betz, Tianchen Qian, Michael Rosenblum
Biostatistics, 2019
[journal]Sensitivity of Adaptive Enrichment Trial Designs to Accrual Rates, Time to Outcome Measurement, and Prognostic Variables
Tianchen Qian, Elizabeth Colantuoni, Aaron Fisher, Michael Rosenblum
Contemporary Clinical Trials Communications, 2017
[journal]Multiple Testing Procedures for Adaptive Enrichment Designs: Combining Group Sequential and Reallocation Approaches
Michael Rosenblum, Tianchen Qian, Yu Du, Huitong Qiu
Biostatistics, 2016
[journal]
U-statistics theory
Summary. In this work we established asymptotic theory and bootstrap validity for U-statistics with two complications: (1) the U-statistic is asymmetrically weighted, and (2) the data is independent but not identically distributed.
On Inference Validity of Weighted U-statistics under Data Heterogeneity
Fang Han, Tianchen Qian
Electronic Journal of Statistics, 2018
[journal]
Alzheimer's disease and related dementia
Sordo, L., Qian, T., Bukhari, S.A., Nguyen, K.M., Woodworth, D.C., Head, E., Kawas, C.H., Corrada, M.M., Montine, T.J. and Sajjadi, S.A. (2023). Characterization of hippocampal sclerosis of aging and its association with other neuropathologic changes and cognitive deficits in the oldest-old. Acta Neuropathologica, 146(3), pp.415-432.
Li, J. X., Nguyen, H. L., Qian, T., Woodworth, D. C., Sajjadi, S. A., & Alzheimer's Disease Neuroimaging Initiative. (2023). Longitudinal hippocampal atrophy in hippocampal sclerosis of aging. Aging Brain, 4, 100092.
Sajjadi, S. A., Qian, T., Bukhari, S., Woodworth, D. C., Montine, T. J., Corrada, M. M., & Kawas, C. H. (2022). Longitudinal clinical and neuropsychological outcomes in limbic predominant age related TDP_43 encephalopathy vs. Alzheimer’s disease from The 90+ Study. Alzheimer's & Dementia, 18, e067366.