addHazardPureRisk {WeightCalibSurvival} | R Documentation |
A pure risk is estimated from additive hazards model fit for a given vector of covariates. Its variance estimate (standard error) is also computed based on influence functions of model coefficients.
addHazardPureRisk(addHazObj, newdata, risk.time, new.risk.col="pureRisk", new.risk.se.col="pureRisk.SE")
addHazObj |
A fitted model from addHazard. |
newdata |
Data frame for covariate-specific pure risk estimation. |
risk.time |
Projection time for pure risk. |
new.risk.col |
New column name added to |
new.risk.se.col |
New column name added to |
The covariates used in addHazObj
must also be in newdata
, and
they must be of the same type.
The data frame newdata
with two additional columns containing
the estimated pure risk and corresponding standard error.
Yei Eun Shin syeeun@gmail.com
Shin YE, Pfeiffer RM Graubard BI, Gail MH. Weight calibration to improve efficiency for estimating pure risks from the additive hazards model with the nested case-control design. Biometrics. 2020;1-13. https://doi.org/10.1111/biom.13413
data(sample_data, package="WeightCalibSurvival") # Set the input arguments ncc.subset <- sample_data[, "ind.ph2"] outcome.var <- "ind.fail" time.vars <- "eventime" timeDep.covars <- c("X1", "X2") timeIndep.covars <- c("Z1", "Z2") anc.covars <- "U" risk.time <- 8 inclProb.var <- "incl.prob" nrisk.var <- "nrisk" fit <- addHazard(sample_data, ncc.subset, outcome.var, time.vars, timeDep.covars, timeIndep.covars, anc.covars, risk.time, inclProb.var=inclProb.var, nrisk.var=nrisk.var) newdata <- sample_data[ncc.subset, ] ret <- addHazardPureRisk(fit$with.calibration, newdata, risk.time) ret[1:5, ]