This function is a helper function for fit_LOCF_landmark_model and fit_LME_landmark_model.
fit_survival_model(
data,
individual_id,
cv_name = NA,
covariates,
event_time,
event_status,
survival_submodel = c("standard_cox", "cause_specific", "fine_gray"),
x_hor
)Data frame containing covariates and time-to-event data, one row for each individual.
Character string specifying the column name in data which contains the individual identifiers
Character string specifying the column name in data that indicates cross-validation fold. If no cross-validation is needed, set this parameter to NA.
Vector of character strings specifying the column names in data_long
which correspond to the covariates
Character string specifying the column name in data which contains the event time
Character string specifying the column name in data which contains the event status (where 0=censoring, 1=event of interest, if there are competing events these are labelled 2 or above). Events at time x_hor should be labelled censored.
Character string specifying which survival submodel to
use. Three options: the standard Cox model i.e. no competing risks ("standard_cox"),
the cause-specific regression model ("cause_specific"), or the Fine Gray
regression model ("fine_gray")
Numeric specifying the horizon time(s)
List containing data_survival and model_survival
data_survival contains the predicted risk of event by the horizon time x_hor.
model_survival contains the outputs from the function used to fit the survival submodel, including the estimated parameters of the model.
For a model using cross-validation, model_survival contains a list of outputs with each
element in the list corresponding to a different cross-validation fold.
For the survival submodel, there are three choices of model:
the standard Cox model, this is a wrapper function for coxph from the package survival
the cause-specific model, this is a wrapper function for CSC from package riskRegression
the Fine Gray model, this is a wrapper function for FGR from package riskRegression
The latter two models estimate the probability of the event of interest in the presence of competing events.
For both the c-index and Brier score calculations, inverse probability censoring weighting (IPCW) is used to create weights which account for the occurrence of censoring. The censoring model assumes for this function is the Kaplan Meier model, i.e. censoring occurs independently of covariates.