Alternating Recurrent Events

Objective

Modeling large-sized event data with two alternating states.  Developed novel improvements to the existing joint frailty models to accommodate multiple event types of large sample sizes conveniently. This is collaborative work with Prof. Douglas Schaubel from the University of Pennsylvania and Prof. Kevin He from the University of Michigan. 

Publication

Wang L, He K, Schaubel DE. Penalized survival models for the analysis of alternating recurrent event data. Biometrics. 2020 

*This paper has won the International Biometric Society Eastern North American Region’s (ENAR) Distinguished Student Paper Awards for the 2019 ENAR Spring Meeting in Philadelphia, PA, USA. 

Software

BivPPL

Forecast COVID-19 Transmissions

Objective

Providing a statistical tool to forecast the spread of infectious diseases with human interventions.  This is a collaborative work with multiple researchers including Prof. Peter Song, Prof. Bhramar Mukherjee,  Prof. Lu Tang, Prof. Debashree Ray,  Dr. Fei Wang, Dr. Bin Zhu,  Dr. Yiwang Zhou, etc. 

Publications

Wang, L., Zhou, Y., He, J., Zhu, B., Wang, F., Tang, L., ... & Song, P. X. (2020). An epidemiological forecast model and software assessing interventions on the COVID-19 epidemic in China. Journal of Data Science, 18(3), 409-432.

Ray, D., Salvatore, M., Bhattacharyya, R., Wang, L., Du, J., Mohammed, S., ... & Mukherjee, B. (2020). Predictions, role of interventions and effects of a historic national lockdown in India’s response to the COVID-19 pandemic: data science call to arms. Harvard data science review, 2020(Suppl 1).

Tang, L., Zhou, Y., Wang, L., Purkayastha, S., Zhang, L., He, J., ... & Song, P. X. K. (2020). A review of multi‐compartment infectious disease models. International Statistical Review, 88(2), 462-513.

Zhou, Y., Wang, L., Zhang, L., Shi, L., Yang, K., He, J., ... & Song, P. (2020). A spatiotemporal epidemiological prediction model to inform county-level COVID-19 risk in the United States. Harvard Data Science Review. 2020.

Software

eSIR

Detect Time-varying Treatment Effect

Objective

This is collaborative work with pharmaceutical biostatisticians resolving a long-lasting problem: how to detect time-varying treatment effects sensitively in a group sequential design? Our solution is to introduce robust max-combo tests to group sequential experiments (GS-MC) which will require nearly the smallest sample size in a set of candidate tests with a controlled false positive rate and an ideal statistical power.  The proposed method avoids tedious simulations to design the experiment.  This is collaborative work with Dr. Cheng Zheng from Zentalis Pharmaceuticals and Dr. Xiaodong Luo from Sanofi, US. 

Publication

Wang, L., Luo, X., & Zheng, C. (2021). A simulation‐free group sequential design with max‐combo tests in the presence of non‐proportional hazards. Pharmaceutical Statistics, 20(4), 879-897.

Software

GSMC

Wearable Device Data to Assess Physical Activities

Objective

Developed a novel statistical method to fast evaluate the key predictors of kids' activities.  This is collaborative work with Prof. Peter Song from the University of Michigan. 

Publication

Wang, L., Song, P. X. K.. (2023+) Multistate rate modeling approach to assess the influence of environmental determinants on children physical activities using accelerometer data. (Under Review)