survPen (version 2.0.1)

predict.survPen: Hazard and Survival prediction from fitted survPen model

Description

Takes a fitted survPen object and produces hazard and survival predictions given a new set of values for the model covariates.

Usage

# S3 method for survPen
predict(
  object,
  newdata,
  newdata.ref = NULL,
  n.legendre = 50,
  conf.int = 0.95,
  do.surv = TRUE,
  type = "standard",
  exclude.random = FALSE,
  get.deriv.H = FALSE,
  ...
)

Value

List of objects:

haz

hazard predicted by the model

haz.inf

lower value for the confidence interval of the hazard based on the Bayesian covariance matrix Vp (Wood et al. 2016)

haz.sup

Upper value for the confidence interval of the hazard based on the Bayesian covariance matrix Vp

surv

survival predicted by the model

surv.inf

lower value for the confidence interval of the survival based on the Bayesian covariance matrix Vp

surv.sup

Upper value for the confidence interval of the survival based on the Bayesian covariance matrix Vp

deriv.H

derivatives wrt to the regression parameters of the cumulative hazard. Useful to calculate standardized survival

HR

predicted hazard ratio ; only when type = "HR"

HR.inf

lower value for the confidence interval of the hazard ratio based on the Bayesian covariance matrix Vp ; only when type = "HR"

HR.sup

Upper value for the confidence interval of the hazard ratio based on the Bayesian covariance matrix Vp ; only when type = "HR"

surv.diff

predicted relative difference ; only when type = "HR"

surv.diff.inf

lower value for the confidence interval of the survival difference based on the Bayesian covariance matrix Vp ; only when type = "HR"

surv.diff.sup

Upper value for the confidence interval of the survival difference based on the Bayesian covariance matrix Vp ; only when type = "HR"

ratio

relative mortality ratio predicted by the model ; only for relative mortality ratio model (type="mult")

ratio.inf

lower value for the confidence interval of the relative mortality ratio based on the Bayesian covariance matrix Vp (Wood et al. 2016); only for relative mortality ratio model (type="mult")

ratio.sup

Upper value for the confidence interval of the relative mortality ratio on the Bayesian covariance matrix Vp; only for relative mortality ratio model (type="mult")

cumul.ratio

cumulative relative mortality ratio predicted by the model ; only for relative mortality ratio model (type="mult")

cumul.ratio.inf

lower value for the confidence interval of the cumulative relative mortality ratio based on the Bayesian covariance matrix Vp (Wood et al. 2016); only for relative mortality ratio model (type="mult")

cumul.ratio.sup

Upper value for the confidence interval of the cumulative relative mortality ratio on the Bayesian covariance matrix Vp; only for relative mortality ratio model (type="mult")

RR

predicted ratio of relative mortality ratios ; only for relative mortality ratio model when type = "HR"

RR.inf

lower value for the confidence interval of the ratio of relative mortality ratios based on the Bayesian covariance matrix Vp ; only for relative mortality ratio model when type = "HR"

RR.sup

Upper value for the confidence interval of the ratio of relative mortality ratios based on the Bayesian covariance matrix Vp ; only for relative mortality ratio model when type = "HR"

Arguments

object

a fitted survPen object as produced by survPen.fit

newdata

data frame giving the new covariates value

newdata.ref

data frame giving the new covariates value for the reference population (used only when type="HR")

n.legendre

number of nodes to approximate the cumulative hazard by Gauss-Legendre quadrature; default is 50

conf.int

numeric value giving the precision of the confidence intervals; default is 0.95

do.surv

If TRUE (the default), the survival (or cumulative ratio for type='mult') and its lower and upper confidence values are computed. Survival computation requires numerical integration and can be time-consuming so if you only want the hazard use do.surv=FALSE; default is TRUE

type,

if type="lpmatrix" returns the design matrix (or linear predictor matrix) corresponding to the new values of the covariates; if equals "HR", returns the predicted HR and survival difference (with CIs) between newdata and newdata.ref; default is "standard" for classical hazard and survival estimation

exclude.random

if TRUE all random effects are set to zero; default is FALSE

get.deriv.H

if TRUE, the derivatives wrt to the regression parameters of the cumulative hazard are returned; default is FALSE

...

other arguments

Details

The confidence intervals noted CI.U are built on the log cumulative hazard scale U=log(H) (efficient scale in terms of respect towards the normality assumption) using Delta method. The confidence intervals on the survival scale are then CI.surv = exp(-exp(CI.U))

References

Wood, S.N., Pya, N. and Saefken, B. (2016), Smoothing parameter and model selection for general smooth models (with discussion). Journal of the American Statistical Association 111, 1548-1575

Examples

library(survPen)
data(datCancer) # simulated dataset with 2000 individuals diagnosed with cervical cancer

f1 <- ~tensor(fu,age,df=c(5,5))

# hazard model
mod1 <- survPen(f1,data=datCancer,t1=fu,event=dead,expected=NULL,method="LAML")

# predicting hazard and survival curves for age 60
nt <- seq(0,5,le=50)
pred <- predict(mod1,data.frame(fu=nt,age=60))
pred$haz
pred$surv

# predicting hazard ratio at 1 year according to age (with reference age of 50)
newdata1 <- data.frame(fu=1,age=seq(30,90,by=1))
newdata.ref1 <- data.frame(fu=1,age=rep(50,times=61))
predHR_1 <- predict(mod1,newdata=newdata1,newdata.ref=newdata.ref1,type="HR")
predHR_1$HR
predHR_1$HR.inf
predHR_1$HR.sup

# predicting hazard ratio at 3 years according to age (with reference age of 50)
# and difference of survival at 3 years
newdata3 <- data.frame(fu=3,age=seq(30,90,by=1))
newdata.ref3 <- data.frame(fu=3,age=rep(50,times=61))
predHR_3 <- predict(mod1,newdata=newdata3,newdata.ref=newdata.ref3,type="HR")

# Hazard ratio
predHR_3$HR
predHR_3$HR.inf
predHR_3$HR.sup


# Difference of survival
predHR_3$diff.surv
predHR_3$diff.surv.inf
predHR_3$diff.surv.sup