stat_kmband  R Documentation 
Adds confidence bands to a Kaplan Meier Estimate of Survival
stat_kmband(
mapping = NULL,
data = NULL,
geom = "kmband",
position = "identity",
show.legend = NA,
inherit.aes = TRUE,
trans = "identity",
firstx = 0,
firsty = 1,
type = "kaplanmeier",
error = "greenwood",
conf.type = "log",
conf.lower = "usual",
start.time = 0,
conf.int = 0.95,
...
)
mapping 
Set of aesthetic mappings created by 
data 
The data to be displayed in this layer. There are three options: If A A 
geom 
The geometric object to use to display the data, either as a

position 
Position adjustment, either as a string naming the adjustment
(e.g. 
show.legend 
logical. Should this layer be included in the legends?

inherit.aes 
If 
trans 
Transformation to apply to the survival probabilities. Defaults to "identity". Other options include "event", "cumhaz", "cloglog", or define your own using trans_new. 
firstx, firsty 
the starting point for the survival curves. By default, the plot program obeys tradition by having the plot start at (0,1). 
type 
an older argument that combined stype and ctype, now deprecated. Legal values were "kaplanmeier" which is equivalent to stype=1, ctype=1, "flemingharrington" which is equivalent to stype=2, ctype=1, and "fh2" which is equivalent to stype=2, ctype=2. 
error 
either the string "greenwood" for the Greenwood formula or "tsiatis" for the Tsiatis formula, (only the first character is necessary). The default is "greenwood". 
conf.type 
One of "none", "plain", "log" (the default), "loglog" or "logit". 
conf.lower 
a character string to specify modified lower limits to the curve, the upper limit remains unchanged. Possible values are "usual" (unmodified), "peto", and "modified". The modified lower limit is based on an "effective n" argument. The confidence bands will agree with the usual calculation at each death time, but unlike the usual bands the confidence interval becomes wider at each censored observation. The extra width is obtained by multiplying the usual variance by a factor m/n, where n is the number currently at risk and m is the number at risk at the last death time. (The bands thus agree with the unmodified bands at each death time.) This is especially useful for survival curves with a long flat tail. The Peto lower limit is based on the same "effective n" argument as the modified limit, but also replaces the usual Greenwood variance term with a simple approximation. It is known to be conservative. 
start.time 
numeric value specifying a time to start calculating survival information. The resulting curve is the survival conditional on surviving to start.time. 
conf.int 
the level for a twosided confidence interval on the survival curve(s). Default is 0.95. 
... 
Other arguments passed to survfit.formula 
This stat is for computing the confidence intervals for the KaplanMeier survival estimate for
rightcensored data. It requires the aesthetic mapping x
for the
observation times and status
which indicates the event status,
0=alive, 1=dead or 1/2 (2=death). Logical status is not supported.
a data.frame with additional columns:
x 
x in data 
ymin 
Lower confidence limit of KM curve 
ymax 
Upper confidence limit of KM curve 
stat_kmband
understands the following aesthetics (required aesthetics
are in bold):
time
The survival times
status
The censoring indicator, see Surv for more information.
alpha
color
linetype
size
library(ggplot2)
sex < rbinom(250, 1, .5)
df < data.frame(time = exp(rnorm(250, mean = sex)), status = rbinom(250, 1, .75), sex = sex)
ggplot(df, aes(time = time, status = status, color = factor(sex))) +
stat_km()
## Examples illustrating the options passed to survfit.formula
p1 < ggplot(df, aes(time = time, status = status))
p1 + stat_km() + stat_kmband(conf.int = .99)
p1 + stat_kmband(error = "greenwood",fill="red",alpha=0.2) +
stat_kmband(error = "tsiatis",fill="blue",alpha=0.2)+ stat_km()
p1 + stat_km() + stat_kmband(conf.type = "loglog")+ stat_kmband(conf.type = "log")
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.