summary.PHcure {penPHcure} | R Documentation |
Summary method for PHcure.object
Description
Produces a summary of a fitted PH cure model
Usage
## S3 method for class 'PHcure'
summary(object, conf.int = c("basic","percentile"), conf.int.level = 0.95,...)
Arguments
object |
an object of class |
conf.int |
a character string indicating the method to compute bootstrapped confidence intervals: |
conf.int.level |
confidence level. By default |
... |
ellipsis to pass extra arguments. |
Value
An object of class summary.PHcure
, a list including the following elements:
N |
the sample size (number of individuals). |
censoring |
the proportion of censored individuals. |
K |
the number of unique failure times. |
isTies |
a logical value, equal to |
conf.int |
a character string indicating the method used to compute the bootstrapped confidence intervals: |
conf.int.level |
confidence level used to compute the bootstrapped confidence intervals. |
nboot |
the number of bootstrap resamples for the construction of the confidence intervals. |
logL |
the value of the log-likelihood for the estimated model. |
CURE |
a matrix with one column containing the estimated regression coefficients in the incidence (cure) component. In case the function |
SURV |
a matrix where in the first column the estimated regression coefficients in the latency (survival) component. In case the function |
Examples
# For reproducibility
set.seed(12)
# If you use R v3.6 or greater, uncomment the following line
# RNGkind(sample.kind="Rounding")
# Generate some data (for more details type ?penPHcure.simulate in your console)
data <- penPHcure.simulate(N=250)
# Fit standard cure model (without inference)
fit <- penPHcure(Surv(time = tstart,time2 = tstop,
event = status) ~ z.1 + z.2 + z.3 + z.4,
cureform = ~ x.1 + x.2 + x.3 + x.4,data = data)
# Use the summary method to see the results
summary(fit)
#
# ------------------------------------------------------
# +++ PH cure model with time-varying covariates +++
# ------------------------------------------------------
# Sample size: 250
# Censoring proportion: 0.5
# Number of unique event times: 125
# Tied failure times: FALSE
#
# log-likelihood: 74.11
#
# ------------------------------------------------------
# +++ Cure (incidence) coefficients +++
# ------------------------------------------------------
# Estimate
# (Intercept) 0.889668
# x.1 -0.972653
# x.2 -0.051580
# x.3 0.714611
# x.4 0.156169
#
# ------------------------------------------------------
# +++ Survival (latency) coefficients +++
# ------------------------------------------------------
# Estimate
# z.1 0.996444
# z.2 -0.048792
# z.3 -1.013562
# z.4 0.079422
# Fit standard cure model (with inference). nboot = 30 bootstrap resamples
# are used to compute the confidence intervals.
fit2 <- penPHcure(Surv(time = tstart,time2 = tstop,
event = status) ~ z.1 + z.2 + z.3 + z.4,
cureform = ~ x.1 + x.2 + x.3 + x.4,data = data,
inference = TRUE,print.details = FALSE,nboot = 30)
# Use the summary method to see the results
summary(fit2)
#
# ------------------------------------------------------
# +++ PH cure model with time-varying covariates +++
# ------------------------------------------------------
# Sample size: 250
# Censoring proportion: 0.5
# Number of unique event times: 125
# Tied failure times: FALSE
#
# log-likelihood: 74.11
#
# ------------------------------------------------------
# +++ Cure (incidence) coefficient estimates +++
# +++ and 95% confidence intervals * +++
# ------------------------------------------------------
# Estimate 2.5% 97.5%
# (Intercept) 0.889668 0.455975 1.092495
# x.1 -0.972653 -1.414194 -0.503824
# x.2 -0.051580 -0.557843 0.304632
# x.3 0.714611 0.206211 1.081819
# x.4 0.156169 -0.011555 0.464841
#
# ------------------------------------------------------
# +++ Survival (latency) coefficient estimates +++
# +++ and 95% confidence intervals * +++
# ------------------------------------------------------
# Estimate 2.5% 97.5%
# z.1 0.996444 0.750321 1.130650
# z.2 -0.048792 -0.204435 0.073196
# z.3 -1.013562 -1.127882 -0.780339
# z.4 0.079422 -0.100677 0.193522
#
# ------------------------------------------------------
# * Confidence intervals computed by the basic
# bootstrap method, with 30 replications.
# ------------------------------------------------------
# By default, confidence intervals are computed by the basic bootstrap method.
# Otherwise, the user can specify the percentile bootstrap method.
summary(fit2,conf.int = "percentile")
#
# ------------------------------------------------------
# +++ PH cure model with time-varying covariates +++
# ------------------------------------------------------
# Sample size: 250
# Censoring proportion: 0.5
# Number of unique event times: 125
# Tied failure times: FALSE
#
# log-likelihood: 74.11
#
# ------------------------------------------------------
# +++ Cure (incidence) coefficient estimates +++
# +++ and 95% confidence intervals * +++
# ------------------------------------------------------
# Estimate 2.5% 97.5%
# (Intercept) 0.889668 0.686842 1.323362
# x.1 -0.972653 -1.441483 -0.531112
# x.2 -0.051580 -0.407791 0.454684
# x.3 0.714611 0.347404 1.223011
# x.4 0.156169 -0.152503 0.323893
#
# ------------------------------------------------------
# +++ Survival (latency) coefficient estimates +++
# +++ and 95% confidence intervals * +++
# ------------------------------------------------------
# Estimate 2.5% 97.5%
# z.1 0.996444 0.862238 1.242567
# z.2 -0.048792 -0.170779 0.106852
# z.3 -1.013562 -1.246785 -0.899242
# z.4 0.079422 -0.034678 0.259521
#
# ------------------------------------------------------
# * Confidence intervals computed by the percentile
# bootstrap method, with 30 replications.
# ------------------------------------------------------
# By default, a 95% confidence level is used. Otherwise, the user can specify
# another confidence level: e.g. 90%.
summary(fit2,conf.int.level = 0.90)
#
# ------------------------------------------------------
# +++ PH cure model with time-varying covariates +++
# ------------------------------------------------------
# Sample size: 250
# Censoring proportion: 0.5
# Number of unique event times: 125
# Tied failure times: FALSE
#
# log-likelihood: 74.11
#
# ------------------------------------------------------
# +++ Cure (incidence) coefficient estimates +++
# +++ and 90% confidence intervals * +++
# ------------------------------------------------------
# Estimate 5% 95%
# (Intercept) 0.889668 0.467864 1.074423
# x.1 -0.972653 -1.397088 -0.618265
# x.2 -0.051580 -0.527389 0.249460
# x.3 0.714611 0.314140 1.028425
# x.4 0.156169 0.033802 0.436361
#
# ------------------------------------------------------
# +++ Survival (latency) coefficient estimates +++
# +++ and 90% confidence intervals * +++
# ------------------------------------------------------
# Estimate 5% 95%
# z.1 0.996444 0.767937 1.125745
# z.2 -0.048792 -0.158821 0.050965
# z.3 -1.013562 -1.120989 -0.800606
# z.4 0.079422 -0.086063 0.180392
#
# ------------------------------------------------------
# * Confidence intervals computed by the basic
# bootstrap method, with 30 replications.
# ------------------------------------------------------