非参数bootstrap方法及其应用

Non-Prarmetric Bootstrap Method for Validation Stabilities of Parameters of Statistical Model

目的:介绍非参数bootstrap方法在验证统计模型参数估计值稳定性方面的应用。方法:采用非参数bootstrap方法验证累积比数L og istic回归模型参数估计值的稳定性。结果:累积比数L og istic回归模型中6个因素的θ∧-β∧/S∧θ均小于25%,可认为模型参数估计值的稳定性较好。结论:采用非参数bootstrap方法验证统计模型参数估计值的稳定性值得推广应用。

Objective：This paper introduced non-parametric bootstrap method for validating stabilities of parameters of statistical model. Medthod： stabilites of parameters of cumulative-odds logistic regression were validated. Result： stabilities of parameters of six factors included in cumulative-odds logistic regression were better because their values of ｜↑^θ-↑^｜/↑^Sθ were all smaller than 25% . Conclusion： non-parametric bootstrap method for validating stabilites of parameters of statistical model is good for popularization.