RSIR: Regularized Sliced Inverse Regression
In abnormally-distributed/cvreg: Cross Validation and Robust Estimation Utilities

Description Usage Arguments Value References

Sliced inverse regression (SIR) is a method used to compute the effective dimension reduction subspace by finding a set of sufficient predictors that contain all of the information in the model matrix X about the outcome Y (Li, 1991). However, in high dimensional scenarios the solution of the SIR algorithm may be difficult and unreliable to compute. Applying regularization has been shown to improve the performance and computational stability of the model (Zhong et al., 2005; Bernard-Michel, et al., 2009a). It has been successfully applied to difficult problems such as analyzing data from Mars (Bernard-Michel, et al., 2009b).

RSIR(
  formula,
  data,
  rank = "all",
  slices = 5,
  ytype = c("numeric", "categorical"),
  target = c("ident", "const", "pca"),
  lambda = 1
)

`formula`	a model formula
`data`	a data frame
`rank`	the desired number of sufficient predictors to return. the default is "all".
`slices`	the number of slices into which the response variable should be split. defaults to 5. for categorical response variables the maximum allowed is the number of response levels minus one. if set above this, it is silently adjusted.
`ytype`	either numeric or categorical
`target`	one of "ident", "const", or "pca". "ident" uses as the shrinkage target the identity matrix, which yields the ridge penalty, (x'x + Iλ)^{-1}. "const" uses as the shrinakge target a matrix with the geometric mean of the variances along the diagonal, and the mean covariance in each off-diagonal cell. "pca"
`lambda`	the regularization parameter. note that the value selected will have quite different impacts depending on the shrinkage target.

an sdr object

Li, K-C. (1991) Sliced inverse regression for dimension reduction. Journal of the American Statistical Association, 86(414), 316-327. doi: 10.1080/01621459.1991.10475035

Zhong, W., Zeng, P., Ma, P., Liu, J.S., & Zhu, M.Y. (2005). RSIR: regularized sliced inverse regression for motif discovery. Bioinformatics, 21 22, 4169-75.

Bernard-Michel, C., Gardes, L., & Girard, S. (2009a). Gaussian Regularized Sliced Inverse Regression. Statistics and Computing, 19, 85-98.

Bernard‐Michel, C., Douté, S., Fauvel, M., Gardes, L., & Girard, S. (2009b). Retrieval of Mars surface physical properties from OMEGA hyperspectral images using regularized sliced inverse regression, J. Geophys. Res., 114, E06005, doi:10.1029/2008JE003171.

abnormally-distributed/cvreg documentation built on May 3, 2020, 3:45 p.m.