Yu, Changhong
2009-Aug-11 15:20 UTC
[R] how to do model validation and calibration for a model fitted by fit.mult.impute?
Dear all, I used fit.mult.impute in Dr. Harrell's Design package to fit a cox ph regression model on five imputed datasets, where all missing predictors were filled by multiple imputation using R package Mice. Are there any functions able to do bootstrapping or cross-validation for the aggregated model? I tried function 'validate' and 'calibrate' in Design package, but found they used the last imputed dataset only instead of all five datasets. Thanks very much. Changhong ================================== P Please consider the environment before printing this e-mail Cleveland Clinic is ranked one of the top hospitals in America by U.S. News & World Report (2008). Visit us online at http://www.clevelandclinic.org for a complete listing of our services, staff and locations. Confidentiality Note: This message is intended for use\...{{dropped:16}}
Possibly Parallel Threads
- multiple imputation with fit.mult.impute in Hmisc - how to replace NA with imputed value?
- fit.mult.impute and quantile regression
- Error message in fit.mult.impute (Hmisc package)
- problem with package rsm: running fit.mult.impute with cph
- rms::cr.setup and Hmisc::fit.mult.impute