...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Journal of Bioinformatics and Computational Biology >DIMENSION REDUCTION OF MICROARRAY GENEEXPRESSION DATA: THE ACCELERATED FAILURETIME MODEL
【24h】

DIMENSION REDUCTION OF MICROARRAY GENEEXPRESSION DATA: THE ACCELERATED FAILURETIME MODEL

机译：微阵列基因表达数据的降维：加速的失效时间模型

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

The construction of the components of Partial Least Squares (PLS) is based on the max-imization of the covariance/correlation between linear combinations of the predictorsand the response. However, the usual Pearson correlation is influenced by outliers in theresponse or in the predictors. To cope with outliers, we replace the Pearson correlationwith the Spearman rank correlation in the optimization criteria of PLS. The rank-basedmethod of PLS is insensitive to outlying values in both the predictors and response,and incorporates the censoring information by using an approach of Nguyen and Rocke(2004) and two approaches of reweighting and mean imputation of Datta et al. (2007).The performance of the rank-based approaches of PLS, denoted by Rank-based Mod-ified Partial Least Squares (RMPLS), Rank-based Reweighted Partial Least Squares(RRWPLS), and Rank-based Mean-Imputation Partial Least Squares (RMIPLS), isinvestigated in a simulation study and on four real datasets, under an Accelerated FailureTime (AFT) model, against their un-ranked counterparts, and several other dimensionreduction techniques. The results indicate that RMPLS is a better dimension reductionmethod than other variants of PLS as well as other considered methods in terms of theminimized cross-validation error of fit and the mean squared error of fit in the presenceof outliers in the response, and is comparable to other variants of PLS in the absence ofoutliers. Supplementary Materials are available at http://www.worldscinet.com/jbcb/
机译：偏最小二乘（PLS）组件的构造基于预测变量和响应的线性组合之间的协方差/相关性的最大化。但是，通常的皮尔逊相关性受响应或预测变量中异常值的影响。为了解决离群值，我们在PLS的优化标准中将Spearman相关替换为Spearman秩相关。 PLS的基于等级的方法对预测值和响应中的偏远值均不敏感，并且使用Nguyen和Rocke（2004）的方法以及Datta等人的两种加权和均值归并的方法来合并检查信息。 （2007）.PLS的基于等级的方法的性能，表示为基于等级的修正偏最小二乘（RMPLS），基于等级的加权加权最小二乘（RRWPLS）和基于等级的均值输入偏最小二乘在加速失效时间（AFT）模型下，针对其未排序的对等方和其他几种降维技术，在模拟研究中和四个真实数据集上对平方（RMIPLS）进行了研究。结果表明，就最小交叉验证拟合误差和在响应中存在离群值的拟合均方误差而言，RMPLS比PLS的其他变体和其他考虑的方法更好的降维方法。在没有异常值的情况下PLS的其他变体。补充材料可在http://www.worldscinet.com/jbcb/获得。

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