survivalExtrapolatePlot: Plot survival data and elicited extrapolated intervals

In SHELF: Tools to Support the Sheffield Elicitation Framework

Plot survival data and elicited extrapolated intervals

Description

Show Kaplan-Meier plot of available data, and credible interval for extrapolated survivor function value S(T)

Usage

survivalExtrapolatePlot(
  survDf,
  myfit1,
  myfit2 = NULL,
  fqDist1 = "best",
  fqDist2 = NULL,
  tTruncate = max(survDf$time),
  tTarget,
  alpha = 0.95,
  useWeights = FALSE,
  groups = levels(survDf$treatment),
  xl = "Time (t)",
  fontsize = 12,
  breakTime = NULL,
  showPlot = TRUE,
  returnPlot = FALSE
)

Arguments

survDf	data frame with individual patient data. Needs three columns with names "time", "event" and "treatment" (in that order). For weighted observations (e.g. using propensity scores), include a fourth column "weights". Values in the "event" column should be 0 for a censored observation, and 1 otherwise. The "treatment" column should be included even if there is only one treatment group, and defined as a factor variable.
myfit1	object of class elicitation, obtained from fitdist function with elicited judgements for the first treatment group.
myfit2	object of class elicitation, obtained from fitdist function with elicited judgements for the second treatment group, if there is on.
fqDist1	fitted distribution family for first treatment group. Options are "normal", "t", "skewnormal", "gamma", "lognormal", "logt","beta", "mirrorgamma", "mirrorlognormal", "mirrorlogt" "hist" (for a histogram fit), and "best" (for best fitting)
fqDist2	fitted distribution family for second treatment group if there is one. Options are "normal", "t", "skewnormal", "gamma", "lognormal", "logt","beta", "mirrorgamma", "mirrorlognormal", "mirrorlogt" "hist" (for a histogram fit), and "best" (for best fitting)
tTruncate	Optional argument to censor all observations at this time point.
tTarget	Target time for extrapolation: judgements are elicited at S(t = tTarget)
alpha	Size of probability interval to plot (100*alpha% interval).
useWeights	set to TRUE if survDf includes column of weights, as described in specification of survDf. This column is passed on to survival::survfit() as the case weights.
groups	Vector of strings for the group labels. Will be extracted from factor levels of treatment column in survDf.
xl	x-axis label in plot
fontsize	font size in plot
breakTime	Optional argument to specify tick mark spacing on x-axis
showPlot	set to TRUE to display the plot
returnPlot	set to TRUE to return the plot as a ggplot object.

Value

a ggplot object, if returnPlot is TRUE

Examples

## Not run: 
sdf <- survival::veteran[, c("time", "status", "trt")]
colnames(sdf) <- c("time", "event", "treatment")
sdf$treatment <- factor(sdf$treatment, labels = c("standard", "test"))

sdf <- survival::veteran[, c("time", "status", "trt")]
colnames(sdf) <- c("time", "event", "treatment")
sdf$treatment <- factor(sdf$treatment, labels = c("standard", "test"))
groupStandardElicitation <- fitdist(vals = c(0.15, 0.2, 0.25),
                                    probs = c(0.25, 0.5, 0.75),
                                    lower = 0,
                                    upper = 1)

groupTestElicitation <- fitdist(vals = c(0.1, 0.15, 0.2),
                                probs = c(0.25, 0.5, 0.75),
                                lower = 0,
                                upper = 1)

survivalExtrapolatePlot(sdf,
                        myfit1 = groupStandardElicitation,
                        myfit2 = groupTestElicitation,
                        fqDist1 = "beta",
                        fqDist2 = "beta",
                        tTruncate = 150,
                        tTarget=200,
                        alpha = 0.95)

## End(Not run)

SHELF documentation built on April 3, 2025, 10:48 p.m.