A0193
Title: Dynamic modelling for multivariate functional and longitudinal data
Authors: Siteng Hao - UC Davis (United States)
Qixian Zhong - Xiamen University (China) [presenting]
Shu-Chin Lin - University of California Davis (United States)
Jane-Ling Wang - University of California Davis (United States)
Abstract: Dynamic interactions among several stochastic processes are common in many scientific fields. It is crucial to model these interactions to understand the dynamic relationship of the corresponding multivariate processes with their derivatives and to improve predictions. In reality, full observations of the multivariate processes are not feasible as measurements can only be taken at discrete locations or time points and often only sparingly and intermittently in longitudinal studies. This results in multivariate longitudinal data measured at different times for different subjects. A time-dynamic model is proposed to handle multivariate longitudinal data by modelling the derivatives of multivariate processes using the values of these processes. Starting with a concurrent linear model, methods are developed to estimate the regression coefficient functions, which can accommodate irregularly measured longitudinal data that are possibly contaminated with noise. This approach can also be applied to settings where all subjects' observational times are the same. The study establishes the convergence rates of the estimators with phase transitions and further illustrates the proposed model through numerical studies.
