摘要
目的针对大气污染与健康关系研究中拟合广义可加模型时的离群点进行诊断并试图减小其影响。方法将经典的稳健M估计方法引入广义可加模型。结果模拟及实例分析可见稳健估计的结果较好。结论在离群点存在时对广义可加模型进行稳健估计是必要的。
In studying the effects of air pollution on human health we use generalized additive models and diagnose the outliers then try to diminish the effect of them. Methods We introduce the elassical robust estimation to generalized additive models. Results The results of robust estimation are better in the simulation and example analysis. Conclusion It is necessary to carry out robust estimation to generalized additive models when there are outliers in data.
出处
《中国卫生统计》
CSCD
北大核心
2007年第3期245-247,270,共4页
Chinese Journal of Health Statistics
基金
山西省高校青年学术带头人基金资助(晋教科2004-13号)
关键词
空气污染
广义可加模型
稳健估计
Air pollution
Generalized additive models
Robust estimation
