Estimating the Ratio of Multivariate Recurrent Event Rates with Applications to a Blood Transfusion Study

• Activity Number: 499
• Type: Contributed
• Date/Time: Wednesday, August 12, 2015 : 8:30 AM to 10:20 AM
• Sponsor: Biometrics Section
• Author(s): Jin Piao* and Jing Ning and Mohammad Rahbar and Sangbum Choi and Chuan Hong and Deborah J. del Junco and Elaheh Rahbar and Erin E. Fox and John Holcomb and Mei-Cheng Wang
• Companies: The University of Texas Health Science Center and MD Anderson Cancer Center and The University of Texas Health Science Center and The University of Texas at Houston and The University of Texas School of Public Health and The University of Texas Health Science Center and Wake Forest University and The University of Texas Health Science Center and The University of Texas Health Science Center and The Johns Hopkins University
• Keywords: Informative censoring ; Multivariate recurrent event ; Rate ratio ; Transfusion medicine

Abstract

Multivariate recurrent event data are commonly encountered in blood transfusion medicine and trauma where patients receive multiple units of various blood products (plasma, platelets, and red blood cells). In this paper, we aim to estimate ratios of multivariate recurrent event rates, accounting for their time-varying characteristics. We use semi-parametric rate models for multivariate recurrent events, which imply multiplicative ratio models. The proposed models and estimating procedures use latent variables to account for multiple sources of informative censoring, such as death, surgical intervention or non-surgical endovascular procedures. The major advantage of the proposed method is that the distributions of the latent variables and the dependence structure between the multivariate recurrent events and informative censoring need not be specified. Thus, the method is robust to complex model assumptions. We establish the asymptotic properties and evaluate the finite sample performance through simulations. We demonstrate application of the proposed method using data from the PRospective Observational Multicenter Major Trauma Transfusion (PROMMTT) study.