Weighted Dirichlet Process Mixture Models to Accommodate Complex Sample Designs for Linear and Quantile Regression.

Weighted Dirichlet Process Mixture Models to Accommodate Complex Sample Designs for Linear and Quantile Regression.
复制标题

DOI:
10.2478/jos-2021-0004
复制
发表时间:
2021-03
影响因子:
1.1
通讯作者:
Xia X
Xia X
中科院分区:
数学4区
文献类型:
--
作者:
Elliott MR;Xia X

文献摘要

参考文献

相似文献

对总体中的数据进行基于标准随机化的推断条件,并对抽样指标的重复抽样性质进行推断。在某些情况下,这些估计值可能非常不稳定;基于贝叶斯模型的方法侧重于人口数量的后验预测分布,潜在地在偏差校正和效率之间提供了更好的平衡。以前在这一领域的工作侧重于均值和线性和广义线性回归参数的估计;这些方法不允许对分位数或分位数回归参数等分布函数进行一般估计。在这里,我们采用了一个扩展的Dirichlet过程混合模型,该模型允许DP先验是作为协变量函数的DP随机基度量的混合。为了适应样本设计的需要,这些模型允许使用许多混合成分,但在数据允许的情况下,为了更有效地估计,这些模型可以缩小到几个成分。我们提供了一个应用程序来估计美国人口中血清二恶英水平与年龄之间的关系,无论是在平均水平上(通过线性回归)还是在二恶英分布上(通过分位数回归),使用国家健康和营养检查调查。
Standard randomization-based inference conditions on the data in the population and makes inference with respect to the repeating sampling properties of the sampling indicators. In some settings these estimators can be quite unstable; Bayesian model-based approaches focus on the posterior predictive distribution of population quantities, potentially providing a better balance between bias correction and efficiency. Previous work in this area has focused on estimation of means and linear and generalized linear regression parameters; these methods do not allow for a general estimation of distributional functions such as quantile or quantile regression parameters. Here we adapt an extended Dirichlet Process Mixture model that allows the DP prior to be a mixture of DP random basis measures that are a function of covariates. These models allow many mixture components when necessary to accommodate the sample design, but can shrink to few components for more efficient estimation when the data allow. We provide an application to the estimation of relationships between serum dioxin levels and age in the US population, either at the mean level (via linear regression) or across the dioxin distribution (via quantile regression) using the National Health and Nutrition Examination Survey.
DOI: 10.1016/j.chemosphere.2013.01.078
发表时间: 2013-05-01
期刊: CHEMOSPHERE
影响因子: 8.8
作者:
Chen, Qixuan;Jiang, Xiaohui;Garabrant, David H.
通讯作者: Garabrant, David H.
DOI: 10.2307/2344652
发表时间: 1979-01-01
影响因子: 2
作者:
HOLT, D;SMITH, TMF
通讯作者: SMITH, TMF
DOI: 10.1214/aos/1176342372
发表时间: 1973-01-01
影响因子: 4.5
作者:
BLACKWELL, D;MACQUEEN, JB
通讯作者: MACQUEEN, JB
DOI: 10.1214/aos/1176342360
发表时间: 1973-01-01
影响因子: 4.5
作者:
FERGUSON, TS
通讯作者: FERGUSON, TS
DOI: 10.1214/10-sts331
发表时间: 2011-05-01
影响因子: 5.7
作者:
Fienberg, Stephen E.
通讯作者: Fienberg, Stephen E.