In this short vignette, we fit a sparse linear regression model with up to \(L > 0\) non-zero effects. Generally, there is no harm in over-stating \(L\) (that is, the method is pretty robust to overfitting), except that computation will grow as \(L\) grows.
Here is a minimal example:
library(susieR)
set.seed(1)
n <- 1000
p <- 1000
beta <- rep(0,p)
beta[c(1,2,300,400)] <- 1
X <- matrix(rnorm(n*p),nrow=n,ncol=p)
y <- X %*% beta + rnorm(n)
res <- susie(X,y,L=10)
plot(coef(res)[-1],pch = 20)
Plot the ground-truth outcomes vs. the predicted outcomes:
Here are some details about the computing environment, including the versions of R, and the R packages, used to generate these results.
sessionInfo()
# R version 4.3.3 (2024-02-29)
# Platform: aarch64-apple-darwin20 (64-bit)
# Running under: macOS 15.4.1
#
# Matrix products: default
# BLAS: /Library/Frameworks/R.framework/Versions/4.3-arm64/Resources/lib/libRblas.0.dylib
# LAPACK: /Library/Frameworks/R.framework/Versions/4.3-arm64/Resources/lib/libRlapack.dylib; LAPACK version 3.11.0
#
# locale:
# [1] en_US.UTF-8/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8
#
# time zone: America/Chicago
# tzcode source: internal
#
# attached base packages:
# [1] stats graphics grDevices utils datasets methods base
#
# other attached packages:
# [1] susieR_0.14.1
#
# loaded via a namespace (and not attached):
# [1] Matrix_1.6-5 gtable_0.3.4 jsonlite_1.8.8
# [4] highr_0.10 dplyr_1.1.4 compiler_4.3.3
# [7] crayon_1.5.2 tidyselect_1.2.1 Rcpp_1.0.12
# [10] parallel_4.3.3 jquerylib_0.1.4 scales_1.3.0
# [13] yaml_2.3.8 fastmap_1.1.1 lattice_0.22-5
# [16] ggplot2_3.5.0 R6_2.5.1 plyr_1.8.9
# [19] generics_0.1.3 mixsqp_0.3-54 knitr_1.45
# [22] tibble_3.2.1 RcppZiggurat_0.1.6 munsell_0.5.0
# [25] bslib_0.6.1 pillar_1.9.0 rlang_1.1.5
# [28] utf8_1.2.4 cachem_1.0.8 reshape_0.8.9
# [31] xfun_0.42 sass_0.4.9 RcppParallel_5.1.10
# [34] cli_3.6.4 magrittr_2.0.3 digest_0.6.34
# [37] grid_4.3.3 irlba_2.3.5.1 lifecycle_1.0.4
# [40] vctrs_0.6.5 Rfast_2.1.0 evaluate_1.0.3
# [43] glue_1.8.0 fansi_1.0.6 colorspace_2.1-0
# [46] rmarkdown_2.26 matrixStats_1.2.0 tools_4.3.3
# [49] pkgconfig_2.0.3 htmltools_0.5.8.1