compositional.mle: Compositional Maximum Likelihood Estimation

Provides composable optimization strategies for maximum likelihood estimation (MLE). Solvers are first-class functions that combine via sequential chaining, parallel racing, and random restarts. Implements gradient ascent, Newton-Raphson, quasi-Newton (BFGS), and derivative-free methods with support for constrained optimization and tracing. Returns 'mle' objects compatible with 'algebraic.mle' for downstream analysis. Methods based on Nocedal J, Wright SJ (2006) "Numerical Optimization" <doi:10.1007/978-0-387-40065-5>.

Version: 1.0.2
Depends: R (≥ 3.5.0), algebraic.mle
Imports: MASS, numDeriv
Suggests: rmarkdown, dplyr, knitr, ggplot2, tibble, testthat (≥ 3.0.0), cli, future, hypothesize
Published: 2026-02-09
DOI: 10.32614/CRAN.package.compositional.mle (may not be active yet)
Author: Alexander Towell ORCID iD [aut, cre]
Maintainer: Alexander Towell <queelius at gmail.com>
BugReports: https://github.com/queelius/compositional.mle/issues
License: MIT + file LICENSE
URL: https://github.com/queelius/compositional.mle, https://queelius.github.io/compositional.mle/
NeedsCompilation: no
Citation: compositional.mle citation info
Materials: README, NEWS
CRAN checks: compositional.mle results

Documentation:

Reference manual: compositional.mle.html , compositional.mle.pdf
Vignettes: Case Studies: MLE for Common Distributions (source, R code)
Getting Started with compositional.mle (source, R code)
The MLE Ecosystem (source, R code)
Designing Optimization Strategies (source, R code)
Theory and Intuition Behind Numerical MLE (source, R code)

Downloads:

Package source: compositional.mle_1.0.2.tar.gz
Windows binaries: r-devel: not available, r-release: not available, r-oldrel: not available
macOS binaries: r-release (arm64): compositional.mle_1.0.2.tgz, r-oldrel (arm64): compositional.mle_1.0.2.tgz, r-release (x86_64): compositional.mle_1.0.2.tgz, r-oldrel (x86_64): compositional.mle_1.0.2.tgz

Linking:

Please use the canonical form https://CRAN.R-project.org/package=compositional.mle to link to this page.