sinvreg function

Dimension Reduction Based on Sliced Inverse Regression

Dimension Reduction Based on Sliced Inverse Regression

sinvreg' is used in the examples for the semimrFullandsemimrOne` functions to obtain initial values based on sliced inverse regression (Li, 1991).

sinvreg(x, y, nslice = NULL)

Arguments

  • x: an n by p matrix of observations where n is the number of observations and p is the number of explanatory variables.
  • y: an n-dimentionsl vector of response values.
  • nslice: number of slices. Default is 10.

Returns

A list containing the following elements: - direction: direction vector.

  • reducedx: reduced x.

  • eigenvalue: eigenvalues for reduced x.

  • nobs: number of observations within each slice.

Examples

# See examples for the 'semimrFull' function.

References

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

See Also

semimrFull, semimrOne

  • Maintainer: Suyeon Kang
  • License: GPL (>= 2)
  • Last published: 2023-09-20

Useful links