Hi All,
I?m using the twang package to estimate ATE propensity scores. These are
being used (inverse probability weighting) in a Cox model estimated by cph
in the rms package with cluster(id) set. I set options to include a
datadist object before running cph.
I want to check for sensitivity to unmeasured covariables by using the
sensuc function in rms with the default arguments.
My syntax is sensuc(fit). The first variable in the right hand side of the
model formula is a binary factor.
The following error is returned:
Current odds ratio for x:u=1
Error in type == "right" : 'type' is missing
My sessionInfo() is:
R version 3.0.2 (2013-09-25)
Platform: x86_64-apple-darwin10.8.0 (64-bit)
locale:
[1] en_US.UTF-8/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8
attached base packages:
[1] grid parallel splines stats graphics grDevices utils
datasets methods base
other attached packages:
[1] rms_4.1-1 SparseM_1.03 Hmisc_3.14-0
Formula_1.1-1 twang_1.3-20 latticeExtra_0.6-26
RColorBrewer_1.0-5 xtable_1.7-1 survey_3.29-5 gbm_2.1
[11] lattice_0.20-24 survival_2.37-7 car_2.0-19
data.table_1.8.10
loaded via a namespace (and not attached):
[1] cluster_1.14.4 MASS_7.3-29 nnet_7.3-7 tools_3.0.2
I?ve looked at the sensuc code.
I can?t understand the error message.
Nathan
--
Nathan Pace, MD, MStat
Department of Anesthesiology
University of Utah
801.581.6393
n.l.pace at utah.edu