A semi-parametric Bayesian model for semi-continuous longitudinal data.

A semi-parametric Bayesian model for semi-continuous longitudinal data.
复制标题

DOI:
10.1002/sim.9359
复制
发表时间:
2022-06-15
影响因子:
2
通讯作者:
Thompson, Wesley K.
Thompson, Wesley K.
中科院分区:
医学3区
文献类型:
--
作者:
Ren, Junting;Tapert, Susan;Fan, Chun Chieh;Thompson, Wesley K.

文献摘要

参考文献

相似文献

半连续数据在模型拟合和解释方面都存在挑战。参数分布可能不适用于数据的极长右尾。协变量的平均效应容易受到极值的影响,可能无法捕获大多数样本的相关信息。我们提出了一种双组分半参数贝叶斯混合模型,其中离散组分由概率质量捕获(通常为零),密度的连续组分由b样条密度的混合物建模,可以灵活地拟合任何数据分布。该模型包括受试者的随机效应,以便应用于纵向数据。我们指定参数的先验分布,并使用r语言编程的Markov Chain Monte Carlo (MCMC) Gibbs-sampling算法进行模型推断。统计推断可以同时对协变量效应的多个分位数进行统计推断,从而提供一个全面的视图。使用各种MCMC采样技术来促进收敛。我们通过模拟和分析全国酒精和青少年神经发育联盟研究(nanda)关于酗酒的数据,证明了该模型的性能和可解释性。
Semi-continuous data present challenges in both model fitting and interpretation. Parametric distributions may be inappropriate for extreme long right tails of the data. Mean effects of covariates, susceptible to extreme values, may fail to capture relevant information for most of the sample. We propose a two-component semi-parametric Bayesian mixture model, with the discrete component captured by a probability mass (typically at zero) and the continuous component of the density modeled by a mixture of B-spline densities that can be flexibly fit to any data distribution. The model includes random effects of subjects to allow for application to longitudinal data. We specify prior distributions on parameters and perform model inference using a Markov Chain Monte Carlo (MCMC) Gibbs-sampling algorithm programmed in R. Statistical inference can be made for multiple quantiles of the covariate effects simultaneously providing a comprehensive view. Various MCMC sampling techniques are used to facilitate convergence. We demonstrate the performance and the interpretability of the model via simulations and analyses on the National Consortium on Alcohol and Neurodevelopment in Adolescence study (NCANDA) data on alcohol binge drinking.
DOI: 10.1534/g3.115.021154
发表时间: 2015-08-18
期刊: G3 (Bethesda, Md.)
影响因子: --
作者:
Montesinos-López OA;Montesinos-López A;Crossa J;Burgueño J;Eskridge K
通讯作者: Eskridge K
DOI: 10.1023/a:1008853808677
发表时间: 1999-01-01
影响因子: 2.2
作者:
Chib, S;Carlin, BP
通讯作者: Carlin, BP
DOI: 10.15288/jsa.1998.59.427
发表时间: 1998-07-01
期刊: JOURNAL OF STUDIES ON ALCOHOL
影响因子: --
作者:
Brown, SA;Myers, MG;Vik, PW
通讯作者: Vik, PW
DOI: 10.15288/jsad.2015.76.895
发表时间: 2015-11-01
影响因子: 3.4
作者:
Brown, Sandra A.;Brumback, T. Y.;Tapert, Susan F.
通讯作者: Tapert, Susan F.
DOI: 10.1198/106186002853
发表时间: 2002-12-01
影响因子: 2.4
作者:
Ruppert, D
通讯作者: Ruppert, D