Software

for implementing methods to adjust for measurement error and misclassification

SIMEX

Software	Procedure / Package	Notes	References
R	Package simex	(a) Performs SIMEX for a wide range of models with X* having classical measurement error and known error variance. (b) Performs MC-SIMEX for categorical X* with a known misclassification matrix. Standard errors can be estimated via jackknife (Stefanski & Cook 1995) or asymptotic approaches (Carroll et al. 1996; Küchenhoff et al. 2007).	Cook & Stefanski (1994) Küchenhoff et al. (2006) Lederer & Küchenhoff (2013)
R	Package simexaft	Performs SIMEX for the accelerated time failure model with covariate X* having classical measurement error and known error variance or repeated measures. X* may be multivariate.	Genz et al. (2011) He et al. (2007)
STATA	Procedures simex and simexplot in package merror	(a) For X* measured in all individuals that, after suitable transformation, satisfies a linear measurement error model together with X₂* measured in a subsample. (b) For X* measured in all individuals with classical measurement error. A subset should have at least one repeat measure. X* and X₂* may be univariate, bivariate or multivariate and may contain excess zeros.	Kipnis et al. (2009)