Computational Statistics

, Volume 26, Issue 3, pp 443–458 | Cite as

maxLik: A package for maximum likelihood estimation in R

  • Arne HenningsenEmail author
  • Ott Toomet
Original Paper


This paper describes the package maxLik for the statistical environment R. The package is essentially a unified wrapper interface to various optimization routines, offering easy access to likelihood-specific features like standard errors or information matrix equality (BHHH method). More advanced features of the optimization algorithms, such as forcing the value of a particular parameter to be fixed, are also supported.


Maximum likelihood Optimization 

JEL Classification



Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Ardia D, Mullen K (2010) DEoptim: global optimization by differential evolution. R package version 2.0–4
  2. Bélisle CJP (1992) Convergence theorems for a class of simulated annealing algorithms on Rd. J Appl Probab 29: 885–895MathSciNetzbMATHCrossRefGoogle Scholar
  3. Berndt EK, Hall BH, Hall RE, Hausman JA (1974) Estimation and inference in nonlinear structural models. Annalysis Soc Meas 3(4): 653–665Google Scholar
  4. Bolker B (2009) bbmle: Tools for general maximum likelihood estimation. R package version 0.9.3
  5. Broyden CG (1970) The convergence of a class of double-rank minimization algorithms. J Inst Math Appl 6: 76–90MathSciNetzbMATHCrossRefGoogle Scholar
  6. Calzolari G, Fiorentini G (1993) Alternative covariance estimators of the standard tobit model. Econ Lett 42(1): 5–13zbMATHCrossRefGoogle Scholar
  7. Carlevaro F, Croissant Y, Hoareau S (2010) mhurdle: estimation of models with limited dependent variables. R package version 0.1.
  8. Croissant Y (2009) truncreg: truncated regression models. R package version 0.1
  9. Croissant Y (2010) pglm: panel generalized linear model. R package version 0.1.
  10. Fletcher R (1970) A new approach to variable metric algorithms. Comput J 13: 317–322zbMATHCrossRefGoogle Scholar
  11. Gay DM (1990) Usage summary for selected optimization routines. Computing science technical report 153, AT&T Bell Laboratories.
  12. Goldfarb D (1970) A family of variable metric updates derived by variational means. Math Comput 24: 23–26MathSciNetzbMATHCrossRefGoogle Scholar
  13. Greene WH (2008) Econometric analysis. 6. Prentice Hall, Englewood CliffsGoogle Scholar
  14. Henningsen A (2010) censReg: censored regression (Tobit) models. R package version 0.5.
  15. Henningsen A, Toomet O (2010) miscTools: miscellanneous small tools and utilities. R package version 0.6.
  16. Nelder JA, Mead R (1965) A simplex algorithm for function minimization. Comput J 7: 308–313zbMATHGoogle Scholar
  17. Nielsen HB, Mortensen SB (2009) ucminf: general-purpose unconstrained non-linear optimization. R package version 1.0
  18. R Development Core Team (2009) R: A language and environment for statistical computing. R foundation for statistical computing. Vienna, Austria., ISBN 3-900051-07-0
  19. Sevcikova H, Raftery A (2010) mlogitBMA: Bayesian Model Averaging for Multinomial Logit Models. R package version 0.1-2
  20. Shanno DF (1970) Conditioning of quasi-newton methods for function minimization. Math Comput 24: 647–656MathSciNetCrossRefGoogle Scholar
  21. Toomet O, Henningsen A (2008) Sample selection models in R: package sampleSelection. J Stat Softw 27(7):1–23. Google Scholar
  22. Toomet O, Henningsen A (2010) maxLik: tools for maximum likelihood estimation. R package version 1.0.

Copyright information

© Springer-Verlag 2010

Authors and Affiliations

  1. 1.Institute of Food and Resource EconomicsUniversity of CopenhagenFrederiksberg CDenmark
  2. 2.Department of Economics, Aarhus School of BusinessUniversity of AarhusÅbyhøjDenmark
  3. 3.Department of EconomicsUniversity of TartuTartuEstonia

Personalised recommendations