负二项回归和Poisson回归在改水降氟效果中的对比分析  

Comparison of Negative Binomial Regression and Poisson Regression in Evaluating the Effect of Water Improvement to Reduce Fluoride

作　　者：楚慧珠[1] 郜艳晖[2] 邹宇华[2] 李伯灵[2] 

机构地区：[1]广东药学院数学教研室,广州510006 [2]广东药学院公共卫生学院

出　　处：《数理医药学杂志》2008年第6期655-657,共3页Journal of Mathematical Medicine

基　　金：广东省卫生厅(粤爱卫办函[2001]7号)基金资助

摘　　要：目的:探讨存在过度离散现象时离散数据的回归分析方法。方法:比较负二项回归和Poisson回归在改水降氟效果评价资料的分析结果和拟合优度。结果:Poisson回归低估参数估计的方差,负二项回归拟合优度较高。结论:负二项回归可用于分析存在过度离散现象的离散数据。Objective： To explore regression analysis models for discrete data with over-dispersion.Methods： Comparing negative-binomial regression to poisson regression in evaluating the effect of water im- provement to reduce fluoride. Results： There were underestimation of variance using poisson regression, and better goodness of fit using negative-binomial regression. Conclusion： Negative-binomial regression model can be used to fit discrete data with over-dispersion.

关 键 词：负二项回归 POISSON回归 过度离散 地方性氟斑牙 

分 类 号：R311[医药卫生—基础医学]