Software
for implementing methods to adjust for measurement error and misclassification
Regression calibration
| Software | Procedure / Package | Notes | References |
|---|---|---|---|
| SAS | NCI macros |
(a) For X* measured in all individuals that, after suitable transformation, satisfies a linear measurement error model, together with an X2* measured in a subsample that has classical measurement error. (b) For X* measured in all individuals with classical measurement error; at least one repeat value should be available. X* and X2* may be univariate, bivariate, or multivariate. |
Kipnis et al (2009) |
| Spiegelman macro %blinplus | For univariate or multivariate X* measured in all individuals in main and validation studies where X* satisfies the linear measurement error model. | Rosner et al (1990) | |
| Spiegelman macro %relibpls8 | For univariate or multivariate X* with repeat measurements. X* satisfies classical measurement error model. | Rosner et al (1992) | |
| Spiegelman macro %rrc | For time-varying covariate X in a Cox regression model. Uses risk-set regression calibration to estimate risk parameters. | Liao et al (2011) | |
| STATA | Procedure rcal in package merror | For generalized linear models with X* having classical measurement error. Options: known error variance, replicate measurements, or instrumental variables available. | Hardin et al (2003) |
| Procedure eivreg | For linear regression where X* has classical measurement error and the error variance is known. | Hardin et al (2003) |