Lu Mao - Research

Research

Funding sources

My research is funded by the following federal grants:

R01HL149875 (PI): Novel Statistical Methods for Complex Time-to-Event Data in Cardiovascular Clinical Trials.
- Total budget: $2,781,980
- Project period: 12/01/2019 – 07/31/2028 (latest renewal on 09/01/2023)
- Key publications (*corresponding author; †student )
  - Mao, L.* and Wang, T.† (2024). Dissecting the restricted mean time in favor of treatment. Journal of Biopharmaceutical Statistics, 34, 111-126. [Slides pdf]
  - Wang, T.†, Mao, L., Cocco, A., and Kim, K. (2024). Statistical inference for time-to-event data in non-randomized cohorts with selective attrition. Statistics in Medicine, 43, 216-232.
  - Mao, L.* (2023). Study design for restricted mean time analysis of recurrent events and death. Biometrics, 10.1111/biom.13923. [Full text pdf; R-package rmt URL]
  - Mao, L.* (2023). Power and sample size calculations for the restricted mean time analysis of prioritized composite endpoints. Statistics in Biopharmaceutical Research, 15, 540-548.
  - Mao, L.* (2023). Study design for restricted mean time analysis of recurrent events and death. Biometrics, 79, 3701-3714. [Full text pdf; R-package rmt URL]
  - Mao, L.* (2023). Nonparametric inference of general while-alive estimands for recurrent events. Biometrics, 79, 1749-1760. [Full text pdf; Sides URL; R-package WA URL; Vignette URL]
  - Mao, L.* (2022). Nonparametric inference of general while-alive estimands for recurrent events. Biometrics, 10.1111/biom.13709. [Full text pdf; Sides pdf; R-package WA URL; Vignette URL]
  - He, Y., Kim S., Mao, L., and Ahn, K.W. (2022). Marginal semiparametric transformation models for clustered multivariate competing risks data. Statistics in Medicine, 41, 5349-5364.
  - Wang, T.† and Mao, L.* (2022). Stratified proportional win-fractions regression analysis. Statistics in Medicine, 41, 5305-5318. [Full text URL pdf; R-package WR URL; Vignette URL]
  - Mao, L.*, Kim, K., and Li, Y.† (2022). On recurrent-event win ratio. Statistical Methods in Medical Research, 10.1177/09622802221084134. [Slides pdf; R-package WR URL; Vignette URL]
  - Mao, L.*, Kim, K., and Miao, X.† (2021). Sample size formula for general win ratio analysis. Biometrics, 78, 1257-1268. [Full text URL; Slides pdf]
  - Mao, L.* and Kim, K. (2021). Statistical models for composite endpoints of death and non-fatal events: a review. Statistics in Biopharmaceutical Research, 13, 260-269.
  - Mao, L.* and Wang, T.† (2020). A class of proportional win-fractions regression models for composite outcomes. Biometrics, 10.1111/biom.13382. [Full text URL; Slides pdf; R-package URL]
  - Li, Y.†, Liang, M., Mao, L.*, and Wang, S. (2021). Robust estimation and variable selection for the accelerated failure time model. Statistics in Medicine, 40, 4473-4491.
  - Dong, G., Mao, L., Huang, B., Gamalo-Siebers, M., Wang, J., Yu, G., and Hoaglin, D. (2020). The inverse-probability-of-censoring weighting (IPCW) adjusted win ratio statistic: an unbiased estimator in the presence of independent censoring. Journal of Biopharmaceutical Statistics, 30, 882-899.
  - Mao, L.* (2020). A unified approach to the calculation of information operators in semiparametric models. Biometrika, 107, 983-995 .
- Software
  - WR: R-package for win ratio analysis of composite time-to-event outcomes.
  - rmt: R-package for the restricted mean time in favor of treatment.
  - WA: R-package for while-alive loss rate for recurrent event in the presence of death.
  - Wcompo: R-package for the proportional means regression of weighted composite endpoint of recurrent event and death.
  - grpseq: R-package for group sequential analysis of clinical trials.

DMS-2015526 (PI): Randomized Trials with Non-Compliance: Extending the Angrist-Imbens-Rubin Framework.
- Total budget: $186,383
- Project period: 07/01/2020 – 06/30/2024
- Key publications (*corresponding author; †student )
  - Mao, L.* (2024). Wilcoxon–Mann–Whitney statistics in randomized trials with non-compliance. Electronic Journal of Statistics, 18, 465-489. [Full text pdf]
  - Mao, L.* (2022). Nonparametric inference of complier quantile treatment effects in randomized trials with imperfect compliance. Biostatistics & Epidemiology, 6, 249-265.
  - Mao, L.* (2022). Identification of the outcome distribution and sensitivity analysis under weak confounder-instrument interaction. Statistics & Probability Letters, 189, 109590. [Full text URL pdf]
  - Mao, L.* (2022). On the relative efficiency of intent-to-treat Wilcoxon–Mann–Whitney test in the presence of non-compliance. Biometrika, 109, 873-880. [Full text URL]

Research topics

My current methodological research focuses on the following areas:

- Generalized "win ratio" methodology for composite endpoints combining death and non-fatal events in clinical trials (see, e.g., Pocock et al., 2012, European Heart Journal).
- Statistical and machine-learning methods for quantitative imaging biomarkers (QIBs). (To learn the myriad of challenges associated with the emerging science of QIB, browse the Quantitative Imaging Biomarkers Alliance website hosted by the Radiological Society of North America.)
- Causal inference in randomized trials with non-compliance. (A seminal paper in this area is written by Angrist, Imbens, and Rubin, 1996, Journal of the American Statistical Association.)

In close alignment with the methods research, I also engage in collaborative studies such as:

- Cardiovascular clinical trials with the Data Coordinating Center.
- Evaluation of diagnostic tests and/or QIBs with investigators from the Departments of Radiology and Medical Physics.
- Behavior intervention studies such as Partner2Lose, a randomized controlled trial to study the effectiveness of partner-assisted weight loss program.

Openings

For graduate students in Statistics or Biomedical Data Science looking for dissertation topics, please email me to make an appointment.