统计与管理学院2015年学术报告第26期

【主  题】 Big data integration in biomedical studies:

【报告人】 Zhu Hongtu 教授

UNC-Chapel Hill Biostatistics and Biomedical Research Imaging Center

【时  间】 2015年6月23日（星期二）15:00－16:00

【地  点】 上海财经大学统计与管理学院大楼1208室

【语  言】 英文

【摘  要】 Motivated by recent work on studying massive imaging, genetic, and clinical data invarious biomedical studies, our group proposes three sets of statistical models including imaging on scalar models, image-on-genetic association models, and prediction models for big data integration. Our statistical models explicitly overcome many challenges in big data integration, brain development, and genetic analysis of high-dimensional brain measurements. We develop some fast estimation procedures to simultaneously estimate parameters of interest. We systematically investigate the asymptotic properties (e.g., consistency and asymptotic normality) of various parameter estimates. Our Monte Carlo simulation and real data analysis have confirmed the excellent performance of our models in different applications. Our novel statistical methods are applicable to a variety of neuroimaging studies and imaging genetic studies of, e.g., neuropsychiatric disorders, major neurodegenerative diseases, substance use disorders, as well as normal brain development.