Sparse semiparametric canonical correlation analysis for data of mixed types.
Sparse semiparametric canonical correlation analysis for data of mixed types.
复制标题
DOI:
10.1093/biomet/asaa007
复制
发表时间:
2020-09
期刊:
影响因子:
2.7
通讯作者:
Gaynanova I
中科院分区:
文献类型:
--
作者:
Yoon G;Carroll RJ;Gaynanova I
Canonical correlation analysis investigates linear relationships between two sets of variables, but often works poorly on modern datasets due to high-dimensionality and mixed data types (continuous/binary/zero-inflated). We propose a new approach for sparse canonical correlation analysis of mixed data types that does not require explicit parametric assumptions. Our main contribution is the use of truncated latent Gaussian copula to model the data with excess zeroes, which allows us to derive a rank-based estimator of latent correlation matrix without the estimation of marginal transformation functions. The resulting semiparametric sparse canonical correlation analysis method works well in high-dimensional settings as demonstrated via numerical studies, and application to the analysis of association between gene expression and micro RNA data of breast cancer patients.
登录
查看更多内容
影响因子:
5.2
作者:
Hua, Kaiyao;Jin, Jiali;Fang, Lin
通讯作者:
Fang, Lin
影响因子:
1
作者:
Chen, Xi;Liu, Han
通讯作者:
Liu, Han
DOI:
10.1186/s13058-015-0666-0
发表时间:
2016-01-07
期刊:
Breast cancer research : BCR
影响因子:
--
作者:
Piggin CL;Roden DL;Gallego-Ortega D;Lee HJ;Oakes SR;Ormandy CJ
通讯作者:
Ormandy CJ
影响因子:
1.4
作者:
Reid, Stephen;Tibshirani, Robert;Friedman, Jerome
通讯作者:
Friedman, Jerome
影响因子:
1.2
作者:
Gorski, Jochen;Pfeuffer, Frank;Klamroth, Kathrin
通讯作者:
Klamroth, Kathrin