esaBcv (version 1.0.1)

esaBcv_package: esaBcv

Description

The esaBcv package provides functions to estimate the latent factors of a given matrix, no matter it is high-dimensional or not. It tries to first estimate the number of factors using Bi-cross-validation and then estimate the latent factor matrix and the noise variances using an Early-stopping-alternation method. The method is proposed by Art B. Owen and Jingshu Wang (2015).

See Also

Owen and Wang (2015) Bi-cross-validation for factor analysis, http://de.arxiv.org/pdf/1503.03515

Examples

data(simdat)
result <- EsaBcv(simdat$Y)
plot(result)