Description Usage Arguments Value Author(s) References Examples
First the starting and stopping TC intervals are determined according to the expected event criteria; ITC intervals are truncated if necessary or dropped if meaningless. Next the dataset is broken up according to the TC intervals.Finally, the dataset is compressed to only the meaningful intervals.
1 2 3 | addtc(dataset, ncov, maxfollow, start_times, stop_times, min_future_events, numevents,
nperson, nmaxint, maxobs, interval_width, nitc_start, itc_start_endpoint, nitc_stop,
itc_stop_endpoint, tti, tts, followup)
|
dataset |
data.frame organized as expected by tc() |
ncov |
number of baseline covariates (including treatment) to be included in model |
maxfollow |
maximum followup for any subject in dataset |
start_times |
vector of ordered times when starting of treatment occurs in dataset |
stop_times |
vector of ordered times when stopping of treatment occurs in dataset |
min_future_events |
minimum number of events expected of future starters(stoppers) of treatment for determining upper bound on starting(stopping) TC intervals |
numevents |
number of events in dataset |
nperson |
number of subjects in dataset |
nmaxint |
maximum number of TC intervals allowed |
maxobs |
maximum number of observations (intervals of time) allowed for dataset |
interval_width |
width of the TC intervals |
nitc_start |
number of ITC starting intervals |
itc_start_endpoint |
vector containing the endpoints of the ITC starting intervals |
nitc_stop |
number of ITC stopping intervals |
itc_stop_endpoint |
Vector containing the endpoints of the ITC starting intervals |
tti |
vector of same length as dataset containing times when starting occurs or 0 if subject does not start |
tts |
vector of same length as dataset containing times when stopping occurs or 0 if subject does not stop |
followup |
vector of same length as dataset containing followup times |
dataset |
data.frame with dataset broken up according to TC intervals |
tstartp |
matrix whose columns are the ITC starting covariate values |
tstopp |
matrix whose columns are the ITC stopping covariate values |
nstartint |
number of TC starting intervals |
startint |
vector containing the TC starting interval endpoints |
nstopint |
number of TC stopping intervals |
stopint |
vector containing the TC stopping interval endpoints |
nitc_start |
number of ITC starting intervals |
itc_start_endpoint |
vector containing the ITC starting interval endpoints |
nitc_stop |
number of ITC stopping intervals |
itc_stop_endpoint |
vector containing the ITC stopping interval endpoints |
James F. Troendle
Troendle, JF, Leifer, E, Zhang Z, Yang, S, and Tewes H (2017) How to Control for Unmeasured Confounding in an Observational Time-To-Event Study With Exposure Incidence Information: the Treatment Choice Cox Model. Statistics in Medicine 36: 3654-3669.
1 2 3 4 5 6 7 8 | ##---- Should be DIRECTLY executable !! ----
##-- ==> Define data, use random,
##-- or do help(data=index) for the standard data sets.
## The function is currently defined as
function (x)
{
}
|
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.