What are the packages in R to do dimensionality reduction?




I am aware of only 1 function called princomp to do PCA in R.Are there other packages in R for dimensionality reduction techniques such as Independant component analysis,Linear discriminant analysis,Canonical Correlation Analysis & Partial Least squares methods


You can check out the following:

  1. ‘dr’ package:
    Description: Functions, methods, and datasets for fitting dimension reduction regression, using slicing (methods SAVE and SIR), Principal Hessian Directions (phd, using residuals and the response), and an iterative IRE. Partial methods, that condition on categorical predictors are also available. A variety of tests, and stepwise deletion of predictors, is also included.
  2. ‘mixOmics’ package:
    Description: We provide statistical integrative techniques and variants to analyse highly dimensional data sets: regularized Canonical Correlation Analysis (‘rCCA’) and sparse Partial Least Squares variants (‘sPLS’) to unravel relationships between two heterogeneous data sets of size (n times p) and (n times q) where the p and q variables are measured on the same samples or individuals n. These data may come from high throughput technologies, such as ‘omics’ data (e.g. transcriptomics, metabolomics or proteomics data) that require an integrative or joint analysis. However, ‘mixOmics’ can also be applied to any other large data sets where p + q >> n. ‘rCCA’ is a regularized version of Canonical Correlation Analysis to deal with the large number of variables. ‘sPLS’ allows variable selection in a one step procedure and two frameworks are proposed: regression and canonical analysis. Numerous graphical outputs are providedto help interpreting the results. Recent methodological developments include: sparse PLSDiscriminant Analysis (‘sPLS-DA’), Independent Principal Component Analysis (‘IPCA’), multilevel analysis using variance decomposition of the data and integration of multiple data sets with regularized Generalised Canonical Correlation Analysis (‘rGCCA’) and variants (sparse ‘GCCA’).