Mixtures of common factor analyzers for high-dimensionaldata with missing values

来源 :The 24th International Workshop on Matrices and Statistics(第 | 被引量 : 0次 | 上传用户:bright202
下载到本地 , 更方便阅读
声明 : 本文档内容版权归属内容提供方 , 如果您对本文有版权争议 , 可与客服联系进行内容授权或下架
论文部分内容阅读
  Mixtures of common factor analyzers (MCFA), thought of as a parsimonious extension of mixture factor analyzers (MFA), have recently been developed as a novel approach to analyzing high-dimensional data, where the number of observations is not very large relative to their dimension. The key idea behind MCFA is to reduce further the number of parameters in the specification of the component-covariance matrices. The occurrence of missing data persists in many scientific investigations and often complicates data analysis. In this work, I present a computationally flexible expectation conditional maximization (ECM) algorithm for maximum likelihood estimation of the MCFA model with partially observed data. To facilitate the implementation, two auxiliary permutation matrices are incorporated into the estimating procedure for exactly extracting the location of observed and missing components of each observation. Practical techniques for the model-based clustering and discriminant analysis are also provided. The proposed methodology is illustrated with the analysis of ozone data and an experimental study on image reconstruction.
其他文献
The growth of solid tumors can be described at a number of different scales from the cell to the organ scales. For a large number of cells, the fluid mechanical
会议
I will discuss our recent model [1] that incorporates cell proliferation with differentiation into different cell types, allowing backward de-differentiation [2
会议
Any coupled network of nonlinear oscillators has a potential to exhibit largescale collective patterns and waves, which are often much larger than that of the c
会议
Cancer remains a leading cause of death with current therapeutic methods. Novel therapies are therefore in urgent needs. One potential method is to use bacteria
会议
会议
We will describe work on epithelial wound healing in drosophila pupae and some more recent work on gap closure in monolayers of MDCK cells or keratinocytes. The
会议
  We propose Partial Correlation Screening (PCS) as a new row-by-row approach. To estimate the i-th row of Ω, 1 ≤ i ≤ p, PCS uses a Screen step and a Clean
会议
In eukaryotes, the absence of telomerase results in telomere shortening, leading to replicative senescence, an arrested state that prevents further cell divisio
会议
  Based upon the Grassman, Taksar and Heyman algorithm [1] and the equivalent Sheskin State Reduction algorithm [2] for finding the stationary distribution of
会议
  The goal of targeted therapeutics and molecular diagnostics is to accumulate drugs or probes at the site of disease in higher quantities relative to other l
会议