########################################## # Inverse-probability weighting # estimator functions ########################################## library("DTR") set.seed(123) data.A1 <- simLDTdata(n = 100, max.c = 2.5, pi.r = 0.5, pi.z = 0.5, lambda = 1.33, alpha = 6.67, beta1 = 0.29, beta2 = -0.67, L = 1.5) data.A2 <- simLDTdata(n = 100, max.c = 2.5, pi.r = 0.5, pi.z = 0.5, lambda = 1.33, alpha = 6.67, beta1 = 0.29, beta2 = -0.67, L = 1.5) LDTdata <- cbind(X = c(rep(0, 100), rep(1, 100)), rbind(data.A1, data.A2)) data("LDTdata", package = "DTR") dim(LDTdata) head(LDTdata) est <- LDTestimate(data = LDTdata) est summary(est) contrast_wald(est, t = 1) plot(est, confidence.interval = TRUE, censored = TRUE) ########################################## # Weighted risk set estimator functions ########################################## data("WRSEdata", package = "DTR") dim(WRSEdata) head(WRSEdata) est <- WRSEestimate(data = WRSEdata) est contrast_wald(est, t = 500) plot(est, confidence.interval = TRUE) ########################################## # Cumulative hazard ratio estimator ## functions ########################################## data("CHRdata", package = "DTR") dim(CHRdata) head(CHRdata) est <- CHRestimate(data = CHRdata, covar = "V1") est$coefficients est summary(est, log.CHR = TRUE) contrast_chr(est, t = 3) plot(est, confidence.interval = TRUE) ########################################## # The weighted log-rank test function ########################################## data("LRdata", package = "DTR") dim(LRdata) head(LRdata) contrast_logrank(data = LRdata) ########################################## # Generalized Cox model functions ########################################## data("PHdata", package = "DTR") dim(PHdata) head(PHdata) fit <- PHfit(data = PHdata, covar = "V") summary(fit) contrast_ph(fit)