Fits generalized linear, asymmetric and robust regression models using spectral majorization and iterative quadratic subproblem solvers. A shared C++ computational core supports dense and sparse designs, automatic intercepts, optional Wald inference and detailed iteration diagnostics. Native code is compiled automatically during package installation.
Spectral majorization for statistical estimation.
This is an independently installable R source package. It contains the R interface and a source snapshot of the shared C++ core. No Julia or Python installation is required. Rcpp and RcppEigen must be installed; source builds require a C++17 compiler. R compiles the core during installation.
install.packages(c("Rcpp", "RcppEigen"))
# Install this source directory with R CMD INSTALL .
library(SpectralMM)
fit <- spectralmm_glm(X, y, family = binomial("logit"))
formula_fit <- spectralmm_glm(y ~ x1 + x2, data = dat, family = binomial("logit"))
summary(fit)
Use help(package="SpectralMM") for the function reference. This directory is generated; edit the canonical repository sources and regenerate it.