泊松回归(英语:Poisson regression)是用来为计数资料和列联表建模的一种回归分析。泊松回归假设反应变量Y是泊松分布,并假设它期望值的对数可被未知参数的线性组合建模。泊松回归模型有时(特别是当用作列联表模型时)又被称作对数-线性模型。
采用了通用估计方程(GEE)方法对泊松回归模型进行参数估计。
Generalized Estimation Equation (GEE) was used to estimate parameters of poisson regression model.
计算年住院分娩率,通过泊松回归调整其他因素和分析不同社会经济地区和不同收入家庭的趋势。
Crude and adjusted annual rates were calculated by means of Poisson regression and were used to define trends across socioeconomic regions and households in different income quintiles.
索赔次数预测模型中通常考虑泊松回归模型,但当索赔次数中出现过离散问题时,泊松回归模型就不再适合。
Poisson regression model is usually used in forecasting claim counts, but when the data appears to be over-dispersed, it will be not suitable.
应用推荐