pre_process: Standardize the given data matrix per column, over the rows,...

In ZhengguoGu/RSCA: Regularized Simultaneous Component Based Data Integration

Description

Standardize the given data matrix per column, over the rows, with multiple imputation for missing data.

Usage

pre_process(DATA, weight)

Arguments

DATA	A data matrix
weight	Whether the data matrix is weighted. weight = TRUE indicates that the data is weighted. Default is weight = FALSE.

Value

a standardized matrix

Note

Weighting a data matrix (i.e., weight = TRUE) is performed as follows. Each cell in the data is divided by the square root of the number of variables.

More details regarding data pre-processing, please see:

Van Deun, K., Smilde, A.K., van der Werf, M.J., Kiers, H.A.L., & Mechelen, I.V. (2009). A structured overview of simultaneous component based data integration. BMC Bioinformatics, 10:246.

The missing values are handled by means of Multivariate Imputation by Chained Equations (MICE). The number of multiple imputation is 5. More details see:

Buuren, S. V., & Groothuis-Oudshoorn, K. (2010). mice: Multivariate imputation by chained equations in R. Journal of statistical software, 1-68.

Examples

## Not run: 
pre_process(matrix(1:12, nrow = 3, ncol = 4))

## End(Not run)

ZhengguoGu/RSCA documentation built on July 5, 2019, 2:26 a.m.