predict.bsplines {xhaz}

Predictions of excess hazard and net Survival from a bsplines object

Description

Function to predict excess hazard and net survival based on an object of class bsplines. The function allows the predictions at several time points but not exceeding the maximum time of follow-up from the baseline model.

Usage

## S3 method for class 'bsplines'
predict(object, new.data = NULL, times.pts = NULL, baseline = TRUE, ...)

Arguments

object

an object of class bsplines

new.data

new.data where is covariates

times.pts

time in year scale to calculate the excess hazard. The default value is NULL. In this case, time variable must be provided in the new.data

baseline

default is survival baseline; put baseline = FALSE to estimate the net survival with covariates

...

additional arguments affecting the predictions of excess hazard and net survival

Value

An object of class predxhaz, which is a list of data.frame. Each element of the list contains the estimates of hazard and survival at a fixed time point. The return of this function can be used to produce graphics of excess hazard or net survival, when times.pts argument is provided. This object contains:

times.pts

the times value in year at which the excess hazard and or the net survival have been estimated

hazard

the excess hazard values based on the model of interest

survival

the net survival values based on the model of interest

Author(s)

Juste Goungounga, Robert Darlin Mba, Nathalie Grafféo and Roch Giorgi

References

Goungounga JA, Touraine C, Grafféo N, Giorgi R; CENSUR working survival group. Correcting for misclassification and selection effects in estimating net survival in clinical trials. BMC Med Res Methodol. 2019 May 16;19(1):104. doi: 10.1186/s12874-019-0747-3. PMID: 31096911; PMCID: PMC6524224. (PubMed)

Touraine C, Grafféo N, Giorgi R; CENSUR working survival group. More accurate cancer-related excess mortality through correcting background mortality for extra variables. Stat Methods Med Res. 2020 Jan;29(1):122-136. doi: 10.1177/0962280218823234. Epub 2019 Jan 23. PMID: 30674229. (PubMed)

Mba RD, Goungounga JA, Grafféo N, Giorgi R; CENSUR working survival group. Correcting inaccurate background mortality in excess hazard models through breakpoints. BMC Med Res Methodol. 2020 Oct 29;20(1):268. doi: 10.1186/s12874-020-01139-z. PMID: 33121436; PMCID: PMC7596976. (PubMed)

See Also

xhaz, print.bsplines, print.constant

Examples

library("survival")
library("numDeriv")
library("survexp.fr")
library("splines")
data("dataCancer", package = "xhaz")   # load the data set in the package

fit.phBS <- xhaz(
        formula = Surv(obs_time_year, event) ~ ageCentre + immuno_trt,
        data = dataCancer, ratetable = survexp.fr,
        interval = c(0, NA, NA, max(dataCancer$obs_time_year)),
        rmap = list(age = 'age', sex = 'sexx', year = 'year_date'),
        baseline = "bsplines", pophaz = "classic")


print(fit.phBS)


predicted <- predict(object = fit.phBS,
                     new.data = dataCancer[1:10,],
                     times.pts = c(seq(0,10,1)),
                     baseline = TRUE)


#a list of predicted hazard and survival at different time points
print(predicted)


#predicted hazard and survival at time points 10 years
print(predicted[[10]])