Title: Bayesian quantile scale on image regression
Authors: Qi Yang - Department of Statistics, the Chinese University of Hong Kong (Hong Kong) [presenting]
Xinyuan Song - Chinese University of Hong Kong (Hong Kong)
Abstract: Imaging data are very common in substantive research, especially in medical studies. The analysis of imaging data can reveal the relationship between the images collected and clinical outcomes of interest. We propose a quantile scale on image regression model to provide a comprehensive analysis of the relationship between a scalar response and imaging predictors. The high dimension of imaging data can be reduced with the aid of efficient functional principle component analysis (FPCA) method. A Bayesian approach together with Markov chain Monte Carlo algorithm is developed to conduct statistical inference. Simulation results demonstrate that the proposed model performs satisfactorily in finite samples. A real example is offered to illustrate the usefulness of the proposed model.