Random effects regression modeling of spatial and longitudinal data

空间和纵向数据的随机效应回归建模

• 批准号: 238682-2010
• 负责人: Ma, Renjun
• 金额: $ 0.87万
• 依托单位: University of New Brunswick
• 依托单位国家: 加拿大
• 项目类别: Discovery Grants Program - Individual
• 财政年份: 2014
• 资助国家: 加拿大
• 起止时间: 2014-01-01 至 2015-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=547063
• 关键词: Random; effects; regression; modeling; spatial

It is well known that the poor health of adolescents is associated with unhealthy life-styles and participation in risky activities such as smoking, alcohol and drug use. Understanding when, why and how risk behaviours are initiated helps deliver effective interventions in schools. As these risk behaviours are usually group behaviours associated with underlying community characteristics, I am interested in the development of multivariate random effects models where random effects can be used to account for such community effects and the association among neighbouring communities. These models help understand the nature of regional disparity across Canada and identify factors which improve social outcomes and reduce inequalities. These findings will help government decision makers geographically target resource allocation, health promotion, education policy and regional planning in an attempt to remediate problem areas.

众所周知，青少年健康状况不佳与不健康的生活方式以及参与吸烟、酗酒和吸毒等危险活动有关。了解危险行为何时、为何以及如何发生有助于在学校实施有效的干预措施。由于这些风险行为通常是与潜在社区特征相关的群体行为，因此我对开发多元随机效应模型感兴趣，其中随机效应可用于解释此类社区效应以及邻近社区之间的关联。这些模型有助于了解加拿大各地地区差异的性质，并确定改善社会成果和减少不平等的因素。这些发现将帮助政府决策者在地理上确定资源分配、健康促进、教育政策和区域规划的目标，以试图解决问题领域。