Model-Based Clustering with Measurement or Estimation Errors

被引:9
作者
Zhang, Wanli [1 ,2 ]
Di, Yanming [1 ]
机构
[1] Oregon State Univ, Dept Stat, Corvallis, OR 97330 USA
[2] Eli Lilly & Co, Shanghai 200021, Peoples R China
基金
美国国家卫生研究院;
关键词
gaussian finite mixture model; clustering analysis; uncertainty; expectation-maximization algorithm; classification boundary; gene expression; RNA-seq; ALGORITHM;
D O I
10.3390/genes11020185
中图分类号
Q3 [遗传学];
学科分类号
071007 ; 090102 ;
摘要
Model-based clustering with finite mixture models has become a widely used clustering method. One of the recent implementations is MCLUST. When objects to be clustered are summary statistics, such as regression coefficient estimates, they are naturally associated with estimation errors, whose covariance matrices can often be calculated exactly or approximated using asymptotic theory. This article proposes an extension to Gaussian finite mixture modeling-called MCLUST-ME-that properly accounts for the estimation errors. More specifically, we assume that the distribution of each observation consists of an underlying true component distribution and an independent measurement error distribution. Under this assumption, each unique value of estimation error covariance corresponds to its own classification boundary, which consequently results in a different grouping from MCLUST. Through simulation and application to an RNA-Seq data set, we discovered that under certain circumstances, explicitly, modeling estimation errors, improves clustering performance or provides new insights into the data, compared with when errors are simply ignored, whereas the degree of improvement depends on factors such as the distribution of error covariance matrices.
引用
收藏
页数:23
相关论文
共 25 条