| Title: | Fit Repeated Linear Regressions |
|---|---|
| Description: | When fitting a set of linear regressions which have some same variables, we can separate the matrix and reduce the computation cost. This package aims to fit a set of repeated linear regressions faster. More details can be found in this blog Lijun Wang (2017) <https://stats.hohoweiya.xyz/regression/2017/09/26/An-R-Package-Fit-Repeated-Linear-Regressions/>. |
| Authors: | Lijun Wang [aut, cre, cph] |
| Maintainer: | Lijun Wang <[email protected]> |
| License: | GPL (>= 2) |
| Version: | 1.3.0 |
| Built: | 2024-11-05 06:24:14 UTC |
| Source: | CRAN |
Fit a set of linear regressions which differ only in one variable.
frlr1(R_X, R_Y, R_COV, num_threads = -1L)frlr1(R_X, R_Y, R_COV, num_threads = -1L)
R_X |
the observation matrix |
R_Y |
the response |
R_COV |
common variables |
num_threads |
number of threads for openmp. If it is -1 (default), it will use all possible threads. |
the fitting results for each regression.
set.seed(123) X = matrix(rnorm(50), 10, 5) Y = rnorm(10) COV = matrix(rnorm(40), 10, 4) frlr1(X, Y, COV)set.seed(123) X = matrix(rnorm(50), 10, 5) Y = rnorm(10) COV = matrix(rnorm(40), 10, 4) frlr1(X, Y, COV)
Fit a set of linear regressions which differ only in two variables.
frlr2(R_X, R_idx1, R_idx2, R_Y, R_COV, num_threads = -1L)frlr2(R_X, R_idx1, R_idx2, R_Y, R_COV, num_threads = -1L)
R_X |
the observation matrix |
R_idx1 |
the first identical feature |
R_idx2 |
the second identical feature |
R_Y |
the response variable |
R_COV |
common variables |
num_threads |
number of threads for openmp. If it is -1 (default), it will use all possible threads. |
the fitting results for each regression.
set.seed(123) X = matrix(rnorm(50), 10, 5) Y = rnorm(10) COV = matrix(rnorm(40), 10, 4) idx1 = c(1, 2, 3, 4, 1, 1, 1, 2, 2, 3) idx2 = c(2, 3, 4, 5, 3, 4, 5, 4, 5, 5) frlr2(X, idx1, idx2, Y, COV)set.seed(123) X = matrix(rnorm(50), 10, 5) Y = rnorm(10) COV = matrix(rnorm(40), 10, 4) idx1 = c(1, 2, 3, 4, 1, 1, 1, 2, 2, 3) idx2 = c(2, 3, 4, 5, 3, 4, 5, 4, 5, 5) frlr2(X, idx1, idx2, Y, COV)