首页> 外文期刊>International Journal of Agricultural and Statistical Sciences >AN IMPROVEMENT OF THE MIXING MCMC ALGORITHM FOR MULTILEVEL LOGISTIC REGRESSION : AN APPLICATION STUDY
【24h】

AN IMPROVEMENT OF THE MIXING MCMC ALGORITHM FOR MULTILEVEL LOGISTIC REGRESSION : AN APPLICATION STUDY

机译:多级逻辑回归混合MCMC算法的改进:应用研究

获取原文
获取原文并翻译 | 示例
           

摘要

This article shows reparameterization technique that is used to improve the mixing of Markov Chain Monte Carlo (MCMC) algorithms. Moreover, one of the main reasons for MCMC method is to identify the correlation evidence between parameters of the model. Therefore, the main objective of the study is to estimate the correlations between a set of fixed effects and their variances. In addition, this study investigates to parameter expansion models including more than one random term, namely random slopes models. This technique will be applied on binary responses data where the sample size of 505 buffaloes collected from three farms. We conclude that the effective sample sizes for all parameters have been improved for this formulation while running time remains approximately the same.
机译:本文显示了用于改善马尔可夫链蒙特卡罗(MCMC)算法的混合的重新传道。 此外,MCMC方法的主要原因之一是识别模型参数之间的相关证据。 因此,该研究的主要目的是估计一组固定效应与其差异之间的相关性。 此外,本研究还研究了参数扩展模型,包括多个随机术语,即随机斜坡模型。 该技术将应用于二进制响应数据,其中来自三个农场的505次水牛的样本大小。 我们得出结论,在运行时间保持大致相同的同时,对所有参数的有效样本尺寸得到改善。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号