initializer.Rd
Standard set-up needed by estimating functions
initializer(
data,
models,
wtq = NULL,
times = NULL,
tau = NULL,
labels = NULL,
subgroup_ps = TRUE,
subsq = NULL,
wt_type = "i",
trim = NULL,
trunc = NULL,
nboot = 0,
seed = 100,
continuous = TRUE,
tau_censor = FALSE,
call
)
The input data frame
A model_specification
object
describing the incoming data,
including the names of the variables containing the outcome (as a time-to-event),
treatment, censoring, and associated models. The outcome and censoring times
should be NA if they are censored). If no identify_missing
statement was
included in the model_specification
, the estimator will default to a complete-case
(listwise deletion)analysis.
quosure containing weights expression
An optional vector of times at which the risk should be computed. Defaults to all observed event times.
The maximum length of follow-up to consider, estimation will not be performed beyond this point.
vector of strings that are used to describe analysis, used for faceting
A logical indicating whether the PS should be re-estimated within the subgroup (default = TRUE)
quosure containing subgroup expression
The type of confounding weight used, "i"=IPTW (default), "n"=IPTW normalized to sum to \(n\) in each treatment group, or a numeric indicating which group to use as a standard in an SMR weight.
A scalar value (between 0 and 0.5) providing the thresholds for symmetrical propensity score trimming. For example, trim = 0.01 will drop observations with propensity scores below to the 1st percentile and above the 99th percentile (default = NULL, no trimming).
A scalar value (between 0 and 1) providing the top percentile at which to truncate confounding weights. For example, trunc = 0.99 will truncate all weights above the 99th percentile, i.e., weights larger than the 99th percentile will be set equal to the 99th percentile (default = NULL, no truncation).
The number of bootstrap resamples to generate. Used only if post-estimation bootstrap is used.
A seed for the random number generator to ensure reproducibility of bootstrap replications
Requests continuous bootstrap weights from a Dirichlet versus discrete weights from a multinomial (default = TRUE)
For backward compatabiity before 0.36.17. Treat censoring at end of follow-up (tau) as a censoring event to be included in censoring models? Defaults to FALSE.
the call to the estimation function
An object containing initial data and parameters for estimating functions