SIMEX- And MCSIMEX-Algorithm for Measurement Error Models

Implementation of the SIMEX-Algorithm by Cook & Stefanski and MCSIMEX by Küchenhoff, Mwalili & Lesaffre.


This pakage for R implements the simex procedure developed by Cook & Stefanski for dealing with measurement error models, as well as the mcsimex for misclassified data developed by Küchenhoff, Mwalili and Lesaffre.

Installation

It can be found on CRAN and installed with

install.packages("simex")

The most current version can be installed via

devtools::install_github("wolfganglederer/simex")

simex NEWS:

Version 1.7:

(by Wolfgang Lederer)

  • Option fitting.method in function simex() now really works properly for "linear" (Wolfgang)
  • Smaller documentation fixes (Wolfgang)
  • Uploaded to Github and moved documentation to roxygen2 (Wolfgang)
  • Added support for proportional odds logistic regression (polr from library MASS) (Chris Lawrence)

Version 1.5:

(by Heidi Seibold & Wolfgang Lederer)

  • Option fitting.method in function simex() now works properly for "linear" (Wolfgang)
  • Measurement errors may now be heteroscedastic. Therefore the input-type had to be changed. The measurement error now has to be a matrix. (Heidi)
  • The functions simex and print.summary.simex were adjusted. (Heidi)

Version 1.4:

(by Ph. Grosjean [email protected])

  • Object classes were renamed 'simex' and 'mcsimex' to match their constructor's names simex() and mcsimex().
  • Interface of mcsimex() has been homogenized with the one of simex(), with fitting.method at the sixth place instead of last one.
  • print() methods now return x invisibly, as they are supposed to do.
  • predict() methods failed when newdata was not provided. Fixed.
  • refit() is now a generic function with methods for objects 'simex' and 'mcsimex'. Its arguments have been reworked to match arguments of simex() and mcsimex() functions (jackknife becomes jackknife.estimation).
  • A NAMESPACE is added and functions that are not supposed to be used by the end-user are now hidden in the namespace (construct.s(), fit.log() and fit.nls()).
  • Documentation has been rewritten to match current R standards. Methods are now documented in the same page as the object creator. 'Overview' is rewritten and renamed 'simex-package'.

References

Küchenhoff, H., Mwalili, S. M. and Lesaffre, E. (2006) A general method for dealing with misclassification in regression: The Misclassification SIMEX. Biometrics, 62, 85 -- 96

Küchenhoff, H., Lederer, W. and E. Lesaffre. (2006) Asymptotic Variance Estimation for the Misclassification SIMEX. Computational Statistics and Data Analysis, 51, 6197 -- 6211

Lederer, W. and Küchenhoff, H. (2006) A short introduction to the SIMEX and MCSIMEX. R News, 6(4), 26--31

Cook, J.R. and Stefanski, L.A. (1994) Simulation-extrapolation estimation in parametric measurement error models. Journal of the American Statistical Association, 89, 1314 -- 1328

Carroll, R.J., Küchenhoff, H., Lombard, F. and Stefanski L.A. (1996) Asymptotics for the SIMEX estimator in nonlinear measurement error models. Journal of the American Statistical Association, 91, 242 -- 250

Carrol, R.J., Ruppert, D., Stefanski, L.A. and Crainiceanu, C. (2006). Measurement error in nonlinear models: A modern perspective., Second Edition. London: Chapman and Hall.

News

simex NEWS:

Version 1.7:

(by Heidi Seibold & Wolfgang Lederer)

  • Option fitting.method in function simex() now really works properly for "linear" (Wolfgang)
  • Smaller documentation fixes (Wolfgang & Heidi)
  • Upload to Github and moving documentation to roxygen2 (Wolfgang)
  • Support for polr() (Chris Lawrence)

Version 1.5:

(by Heidi Seibold & Wolfgang Lederer)

  • Option fitting.method in function simex() now works properly for "linear" (Wolfgang)

  • Measurement errors may now be heteroscedastic. Therefore the input-type had (Heidi) to be changed. The measurement error now has to be a matrix.

  • The functions simex and print.summary.simex were adjusted. (Heidi)

Version 1.4:

(by Ph. Grosjean [email protected])

  • Object classes were renamed 'simex' and 'mcsimex' to match their constructor's names simex() and mcsimex().

  • Interface of mcsimex() has been homogenized with the one of simex(), with fitting.method at the sixth place instead of last one.

  • print() methods now return x invisibly, as they are supposed to do.

  • predict() methods failed when newdata was not provided. Fixed.

  • refit() is now a generic function with methods for objects 'simex' and 'mcsimex'. Its arguments have been reworked to match arguments of simex() and mcsimex() functions (jackknife becomes jackknife.estimation).

  • A NAMESPACE is added and functions that are not supposed to be used by the end-user are now hidden in the namespace (construct.s(), fit.log() and fit.nls()).

  • Documentation has been rewritten to match current R standards. Methods are now documented in the same page as the object creator. 'Overview' is rewritten and renamed 'simex-package'.

Reference manual

It appears you don't have a PDF plugin for this browser. You can click here to download the reference manual.

install.packages("simex")

1.7 by Wolfgang Lederer, 2 years ago


https://github.com/wolfganglederer/simex


Report a bug at https://github.com/wolfganglederer/simex/issues


Browse source code at https://github.com/cran/simex


Authors: Wolfgang Lederer <[email protected]> , Heidi Seibold <[email protected]> , Helmut Küchenhoff <[email protected]>


Documentation:   PDF Manual  


GPL-3 license


Imports stats, graphics

Suggests mgcv, nlme, MASS


Imported by DFIT, SurvDisc.

Depended on by support.CEs.

Enhanced by memisc, texreg.


See at CRAN