Ultrahigh dimensional time course feature selection

Xu, Peirong; Zhu, Lixing; Li, Yang

doi:10.1111/biom.12137

Cited by 17 publications

(16 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the lower dimensional case, classical linear GEE or penalized GEE can be used. For the ultra-high dimensional case, screening methods for longitudinal data such as the nonparametric independence screening and structure identification method from Cheng et al (2014) or Xu et al (2014) may be used to obtain initial values. In our numerical studies, starting values obtained from the sure independence screening (SIS) procedure in Fan and Lv (2008) work quite well.…”

Section: An Efficient Algorithmmentioning

confidence: 99%

Ultra high‐dimensional semiparametric longitudinal data analysis

Green

Lian

et al. 2020

Biometrics

View full text Add to dashboard Cite

As ultra-high dimensional longitudinal data is becoming ever more apparent in fields such as public health, information systems, and bioinformatics, developing flexible methods with a sparse set of important variables is of high interest. In this setting, the dimension of the covariates can potentially grow exponentially with respect to the number of clusters. This dissertation research considers a flexible semiparametric approach, namely, partially linear single-index models, for ultra-high dimensional longitudinal data. Most importantly, we allow not only the partially linear covariates, but also the single-index covariates within the unknown flexible function estimated nonparametrically to be ultrahigh dimensional. Using penalized generalized estimating equations, this approach can capture correlation within subjects, can perform simultaneous variable selection and estimation with a smoothly clipped absolute deviation penalty, and can capture nonlinearity and potentially some interactions among predictors. We establish asymptotic theory for the estimators including the oracle property in ultra-high dimension for both the partially linear and nonparametric components. An efficient algorithm is presented to handle the computational challenges, and we show the effectiveness of our method and algorithm via a simulation study and yeast cell cycle gene expression data. In addition, we develop an alternative solution methodology via the penalized quadratic inference function with partially linear single-index models for ultra-high dimensional longitudinal data. This methodology can improve the estimation efficiency when the working correlation structure is misspecified. Performance is demonstrated via a simulation study and analysis of a genomic dataset.

show abstract

Section: An Efficient Algorithmmentioning

confidence: 99%

Ultra high‐dimensional semiparametric longitudinal data analysis

Green

Lian

et al. 2020

Biometrics

View full text Add to dashboard Cite

show abstract

“…Thus, feature screening is a necessary step before conducting confirmatory statistical analysis. Xu et al [53] proposed a feature screening procedure for longitudinal data based on marginal generalized estimating equation methods and Song et al [45] extended the nonparametric independence screening procedure for time-varying coefficient model with longitudinal data. For longitudinal data analysis, it is of importance to incorporate the within-subject correlation and heteroscedasticity to improve existing procedure by reducing false negative rate.…”

Section: Concluding Remarks and Future Researchmentioning

confidence: 99%

A selective overview of feature screening for ultrahigh-dimensional data

Liu

Zhong

2015

Sci. China Math.

View full text Add to dashboard Cite

High-dimensional data have frequently been collected in many scientific areas including genomewide association study, biomedical imaging, tomography, tumor classifications, and finance. Analysis of high-dimensional data poses many challenges for statisticians. Feature selection and variable selection are fundamental for high-dimensional data analysis. The sparsity principle, which assumes that only a small number of predictors contribute to the response, is frequently adopted and deemed useful in the analysis of high-dimensional data. Following this general principle, a large number of variable selection approaches via penalized least squares or likelihood have been developed in the recent literature to estimate a sparse model and select significant variables simultaneously. While the penalized variable selection methods have been successfully applied in many high-dimensional analyses, modern applications in areas such as genomics and proteomics push the dimensionality of data to an even larger scale, where the dimension of data may grow exponentially with the sample size. This has been called ultrahigh-dimensional data in the literature. This work aims to present a selective overview of feature screening procedures for ultrahigh-dimensional data. We focus on insights into how to construct marginal utilities for feature screening on specific models and motivation for the need of model-free feature screening procedures.

show abstract

“…One commonly used strategy is to stratify time series data into separate time points and then analyze these points separately. This approach may lead to inefficiency in statistical power by ignoring the highly correlated structure of gene expression values across time and thus result in failure to detect patterns of change across time [1–3].…”

Section: Introductionmentioning

confidence: 99%

Feature Selection for Longitudinal Data by Using Sign Averages to Summarize Gene Expression Values over Time

Tian

Wang

2019

BioMed Research International

View full text Add to dashboard Cite

With the rapid evolution of high-throughput technologies, time series/longitudinal high-throughput experiments have become possible and affordable. However, the development of statistical methods dealing with gene expression profiles across time points has not kept up with the explosion of such data. The feature selection process is of critical importance for longitudinal microarray data. In this study, we proposed aggregating a gene’s expression values across time into a single value using the sign average method, thereby degrading a longitudinal feature selection process into a classic one. Regularized logistic regression models with pseudogenes (i.e., the sign average of genes across time as predictors) were then optimized by either the coordinate descent method or the threshold gradient descent regularization method. By applying the proposed methods to simulated data and a traumatic injury dataset, we have demonstrated that the proposed methods, especially for the combination of sign average and threshold gradient descent regularization, outperform other competitive algorithms. To conclude, the proposed methods are highly recommended for studies with the objective of carrying out feature selection for longitudinal gene expression data.

show abstract

Ultrahigh dimensional time course feature selection

Cited by 17 publications

References 19 publications

Ultra high‐dimensional semiparametric longitudinal data analysis

Ultra high‐dimensional semiparametric longitudinal data analysis

A selective overview of feature screening for ultrahigh-dimensional data

Feature Selection for Longitudinal Data by Using Sign Averages to Summarize Gene Expression Values over Time

Contact Info

Product

Resources

About