Hmisc (version 2.2-0)

event.chart: Flexible Event Chart for Time-to-Event Data

Description

Creates an event chart on the current graphics device. Also, allows user to plot legend on plot area or on separate page. Contains features useful for plotting data with time-to-event outcomes Which arise in a variety of studies including randomized clinical trials and non-randomized cohort studies. This function can use as input a matrix or a data frame, although greater utility and ease of use will be seen with a data frame.

Usage

event.chart(data, subset.r = 1:dim(data)[1], subset.c = 1:dim(data)[2],
        sort.by = NA, sort.ascending =TRUE,
        sort.na.last =TRUE, sort.after.subset =TRUE,
        y.var = NA, y.var.type = 'n',
        y.jitter =FALSE, y.jitter.factor = 1,
        y.renum =FALSE, NA.rm =FALSE, x.reference = NA,
        now = max(data[,subset.c], na.rm =TRUE),
        now.line =FALSE, now.line.lty = 2,
        now.line.lwd = 1, now.line.col = 1, pty='m',
        date.orig = c(1,1,1960), titl = 'Event Chart',

y.idlabels = NA, y.axis = 'auto', y.axis.custom.at = NA, y.axis.custom.labels = NA, y.julian =FALSE, y.lim.extend = c(0,0), y.lab = ifelse(is.na(y.idlabels), '' , as.character(y.idlabels)),

x.axis.all =TRUE, x.axis = 'auto', x.axis.custom.at = NA, x.axis.custom.labels = NA, x.julian =FALSE, x.lim.extend = c(0,0), x.scale = 1, x.lab = ifelse(x.julian, 'Follow-up Time', 'Study Date'),

line.by = NA, line.lty = 1, line.lwd = 1, line.col = 1, line.add = NA, line.add.lty = NA, line.add.lwd = NA, line.add.col = NA, point.pch = 1:length(subset.c), point.cex = rep(0.6,length(subset.c)), point.col = rep(1,length(subset.c)),

legend.plot =FALSE, legend.location = 'o', legend.titl = titl, legend.titl.cex = 3.0, legend.titl.line = 1.0, legend.point.at = list(x = c(5,95), y = c(95,30)), legend.point.pch = point.pch, legend.point.text = ifelse(rep(is.data.frame(data), length(subset.c)), names(data[,subset.c]), subset.c), legend.cex = 2.5, legend.bty = 'n', legend.line.at = list(x = c(5,95), y = c(20,5)), legend.line.text = names(table(as.character(data[,line.by]), exclude = c('','NA'))), legend.line.lwd = line.lwd, legend.loc.num = 1,

...)

event.convert(data2, event.time = 1, event.code = 2)

Arguments

data
a matrix or data frame with rows corresponding to subjects and columns corresponding to variables. Note that for a data frame or matrix containing multiple time-to-event data (e.g., time to recurrence, time to death, and time to last follow-up), one colu
data2
a matrix or dataframe with at least 2 columns; by default, the first column contains the event time and the second column contains the k event codes (e.g. 1=dead, 0=censord)
subset.r
subset of rows of original matrix or data frame to place in event chart. Logical arguments may be used here (e.g., treatment.arm == 'a', if the data frame, data, has been attached to the search directory; otherwise, data$treatment.arm == "a")
subset.c
subset of columns of original matrix or data frame to place in event chart; if working with a data frame, a vector of data frame variable names may be used for subsetting purposes (e.g., c('randdate', 'event1').
sort.by
column(s) or data frame variable name(s) with which to sort the chart's output. The default is NA, thereby resulting in a chart sorted by original row number.
sort.ascending
logical flag (which takes effect only if the argument sort.by is utilized). If TRUE (default), sorting is done in ascending order; if F, descending order.
sort.na.last
logical flag (which takes effect only if the argument sort.by is utilized). If T (default), NA values are considered as last values in ordering.
sort.after.subset
logical flag (which takes effect only if the argument sort.by is utilized). If F, sorting data (via sort.by specified variables or columns) will be performed prior to row subsetting (via subset.r); if T (default), row subsetting of original data will be d
y.var
variable name or column number of original matrix or data frame with which to scale y-axis. Default is NA, which will result in equally spaced lines on y-axis (based on original data or sorted data if requested by sort.by). Otherwise, location of lines on
y.var.type
type of variable specified in y.var (which will only take effect if argument y.var is utilized). If 'd', specifed variable is a date (either numeric julian date or an S-Plus dates object); if 'n', specifed variable is numeric (e.g., systolic blood pressu
y.jitter
logical flag (which takes effect only if the argument y.var is utilized). Due to potential ties in y.var variable, y.jitter (when T) will jitter the data to allow discrimination between observations at the possible cost of producing slightly inaccurate da
y.jitter.factor
an argument used with the y.jitter function to scale the range of added noise. Default is 1.
y.renum
logical flag. If T, subset observations are listed on y-axis from 1 to length(subset.r); if F (default), subset observations are listed on y-axis in original form. As an example, if subset.r = 301:340 and y.renum ==TRUE, y-axis will be shown as 1 throug
NA.rm
logical flag. If T, subset observations which have NA for each variable specified in subset.c will not have an entry on the y-axis. Also, if the following argument, x.reference, is specified, observations with missing x.reference values will also not ha
x.reference
column of original matrix or data frame with which to reference the x-axis. That is, if specified, all columns specified in subset.c will be substracted by x.reference. An example may be to see the timing of events before and after treatment or to see ti
now
the 'now' date which will be used for top of y-axis when creating the Goldman eventchart (see reference below). Default is max(data[, subset.c], na.rm =TRUE).
now.line
logical flag. A feature utilized by the Goldman Eventchart. When x.reference is specified as the start of follow-up and y.var = x.reference, then the Goldman chart can be created. This argument, if T, will cause the plot region to be square, and will dr
now.line.lty
line type of now.line.
now.line.lwd
line width of now.line.
now.line.col
color of now.line.
pty
graph option, pty='m' is the default; use pty='s' for the square looking Goldman's event chart.
date.orig
date of origin to consider if dates are in julian, SAS , or S-Plus dates object format; default is January 1, 1960 (which is the default origin used by both S-Plus and SAS). Utilized when either y.julian =FALSE or x.julian = F.
titl
title for event chart. Default is 'Event Chart'.
y.idlabels
column or data frame variable name used for y-axis labels. For example, if c('pt.no') is specified, patient ID (stored in 'pt.no') will be seen on y-axis labels instead of sequence specified by subset.r. This argument takes precedence over both y.axis='
y.axis
character string specifying whether program will control labelling of y-axis (with argument 'auto'), or if user will control labelling (with argument 'custom'). If 'custom' is chosen, user must specify location and text of labels using y.axis.custom.at a
y.axis.custom.at
user-specified vector of y-axis label locations. Must be used when y.axis = 'custom'; will not be used otherwise.
y.axis.custom.labels
user-specified vector of y-axis labels. Must be used when y.axis = 'custom'; will not be used otherwise.
y.julian
logical flag (which will only be considered if y.axis == 'auto' and (!is.na(y.var) & y.var.type== 'd'). If F (default), will convert julian numeric dates or S-Plus dates objects into 'mm/dd/yy' format for the y-axis labels. If T, dates will be printed i
y.lim.extend
two-dimensional vector representing the number of units that the user wants to increase ylim on bottom and top of y-axis, respectively. Default = c(0,0). This argument will not take effect if the Goldman chart is utilized.
y.lab
single label to be used for entire y-axis. Default will be the variable name or column number of y.idlabels (if non-missing) and blank otherwise.
x.axis.all
logical flag. If T (default), lower and upper limits of x-axis will be based on all observations (rows) in matrix or data frame. If F, lower and upper limits will be based only on those observations specified by subset.r (either before or after sorting d
x.axis
character string specifying whether program will control labelling of x-axis (with argument 'auto'), or if user will control labelling (with argument 'custom'). If 'custom' is chosen, user must specify location and text of labels using x.axis.custom.at a
x.axis.custom.at
user-specified vector of x-axis label locations. Must be used when x.axis == 'custom'; will not be used otherwise.
x.axis.custom.labels
user-specified vector of x-axis labels. Must be used when x.axis == 'custom'; will not be used otherwise.
x.julian
logical flag (which will only be considered if x.axis == 'auto'). If F (default), will convert julian dates or S-plus dates objects into 'mm/dd/yy' format for the x-axis labels. If T, dates will be printed in julian (numeric) format. NOTE: This argumen
x.lim.extend
two-dimensional vector representing the number of time units (usually in days) that the user wants to increase xlim on left-hand side and right-hand side of x-axis, respectively. Default = c(0,0). This argument will not take effect if the Goldman chart
x.scale
a factor whose reciprocal is multiplied to original units of the x-axis. For example, if the original data frame is in units of days, x.scale = 365 will result in units of years (notwithstanding leap years). Default is 1.
x.lab
single label to be used for entire x-axis. Default will be 'On Study Date' if x.julian ==FALSE and 'Time on Study' if x.julian = T.
line.by
column or data frame variable name for plotting unique lines by unique values of vector (e.g., specify c('arm') to plot unique lines by treatment arm). Can take at most one column or variable name. Default is NA which produces identical lines for each pa
line.lty
vector of line types corresponding to ascending order of line.by values. If line.by is specified, the vector should be the length of the number of unique values of line.by. If line.by is NA, only line.lty[1] will be used. The default is 1.
line.lwd
vector of line widths corresponding to ascending order of line.by values. If line.by is specified, the vector should be the length of the number of unique values of line.by. If line.by is NA, only line.lwd[1] will be used. The default is 1.
line.col
vector of line colors corresponding to ascending order of line.by values. If line.by is specified, the vector should be the length of the number of unique values of line.by. If line.by is NA, only line.col[1] will be used. The default is 1.
line.add
a 2xk matrix with k=number of pairs of additional line segments to add. For example, if it is of interest to draw additional line segments connecting events one and two, two and three, and four and five, (possibly with different colors), an appropriate li
line.add.lty
a kx1 vector corresponding to the columns of line.add; specifies the line types for the k line segments.
line.add.lwd
a kx1 vector corresponding to the columns of line.add; specifies the line widths for the k line segments.
line.add.col
a kx1 vector corresponding to the columns of line.add; specifies the line colors for the k line segments.
point.pch
vector of pch values for points representing each event. If similar events are listed in multiple columns (e.g., regular visits or a recurrent event), repeated pch values may be listed in the vector (e.g., c(2,4,rep(183,3))). If length(point.pch) < lengt
point.cex
vector of size of points representing each event. If length(point.cex) < length(subset.c), point.cex will be repeated until lengths are equal; a warning message will verify this condition.
point.col
vector of colors of points representing each event. If length(point.col) < length(subset.c), point.col will be repeated until lengths are equal; a warning message will verify this condition.
legend.plot
logical flag; if T, a legend will be plotted. Location of legend will be based on specification of legend.location along with values of other arguments listed below. Default is F (i.e., no legend plotting).
legend.location
will be used only if legend.plot=T. If 'o' (default), a one-page legend will precede the output of the chart. The user will need to hit in order for the event chart to be displayed. This feature is possible due to the dev.askoption. If 'i',
legend.titl
title for the legend; default is title to be used for main plot. Only used when legend.location = 'o'.
legend.titl.cex
size of text for legend title. Only used when legend.location = 'o'.
legend.titl.line
line location of legend title dictated by mtext function with outer=FALSE option; default is 1.0. Only used when legend.location = 'o'.
legend.point.at
location of upper left and lower right corners of legend area to be utilized for describing events via points and text.
legend.point.pch
vector of pch values for points representing each event in the legend. Default is point.pch.
legend.point.text
text to be used for describing events; the default is setup for a data frame, as it will print the names of the columns specified by subset.c .
legend.cex
size of text for points and event descriptions. Default is 2.5 which is setup for legend.location = 'o'. A much smaller cex is recommended (possibly 0.75) for use with legend.location = 'i' or legend.location = 'l'.
legend.bty
option to put a box around the legend(s); default is to have no box (legend.bty = 'n'). Option legend.bty = 'o' will produce a legend box.
legend.line.at
if line.by was specified (with legend.location = 'o' or legend.location = 'i'), this argument will dictate the location of the upper left and lower right corners of legend area to be utilized for describing the different line.by values (e.g., treatment.ar
legend.line.text
text to be used for describing line.by values; the default are the names of the unique non-missing line.by values as produced from the table function.
legend.line.lwd
vector of line widths corresponding to line.by values.
legend.loc.num
number used for locator argument when legend.locator = 'l'. If 1 (default), user is to locate only the top left corner of the legend box. If 2, user is to locate both the top left corner and the lower right corner. This will be done twice when line.by
event.time
the column number in data contains the event time
event.code
the column number in data contains the event code
...
additional par arguments for use in main plot.

Side Effects

an event chart is created on the current graphics device. If legend.plot =TRUE and legend.location = 'o', a one-page legend will precede the event chart. Please note that par parameters on completion of function will be reset to par parameters existing prior to start of function.

Details

if you want to put, say, two eventcharts side-by-side, in a plot region, you should not set up par(mfrow=c(1,2)) before running the first plot. Instead, you should add the argument mfg=c(1,1,1,2) to the first plot call followed by the argument mfg=c(1,2,1,2) to the second plot call.

if dates in original data frame are in a specialized form (eg., mm/dd/yy) of mode CHARACTER, the user must convert those columns to become class dates or julian numeric mode (see ?dates for more information). For example, in a data frame called testdata, with specialized dates in columns 4 thru 10, the following code could be used: as.numeric(dates(testdata[,4:10]). This will convert the columns to numeric julian dates based on the function's default origin of January 1, 1960. If original dates are in class dates or julian form, no extra work is necessary.

In the survival analysis, the data typically come in two columns: one column containing survival time and the other containing censoring indicator or event code. The event.convert function converts this type of data into multiple columns of event times, one column of each event type, suitable for the event.chart function.

References

Lee J.J., Hess, K.R., Dubin, J.A. (2000). Extensions and applications of event charts. The American Statistician, 54:1, 63--70.

Dubin, J.A., Lee, J.J., Hess, K.R. (1997). The Utility of Event Charts. Proceedings of the Biometrics Section, American Statistical Association.

Dubin, J.A., Muller H-G, Wang J-L (2001). Event history graphs for censored survival data. Statistics in Medicine, 20: 2951--2964.

Goldman, A.I. (1992). EVENTCHARTS: Visualizing Survival and Other Timed-Events Data. The American Statistician, 46:1, 13--18.

See Also

event.history

Examples

Run this code
# The sample data set is an augmented CDC AIDS dataset (ASCII)
# which is used in the examples in the help file.  This dataset is 
# described in Kalbfleisch and Lawless (JASA, 1989).
# Here, we have included only children 4 years old and younger.
# We have also added a new field, dethdate, which
# represents a fictitious death date for each patient.  There was
# no recording of death date on the original dataset.
#   
# All dates are julian with julian=0 being 
# January 1, 1960, and julian=14000 being 14000 days beyond
# January 1, 1960 (i.e., May 1, 1998).


cdcaids <- data.frame(
age=c(4,2,1,1,2,2,2,4,2,1,1,3,2,1,3,2,1,2,4,2,2,1,4,2,4,1,4,2,1,1,3,3,1,3),
infedate=c(
7274,7727,7949,8037,7765,8096,8186,7520,8522,8609,8524,8213,8455,8739,
8034,8646,8886,8549,8068,8682,8612,9007,8461,8888,8096,9192,9107,9001,
9344,9155,8800,8519,9282,8673),
diagdate=c(
8100,8158,8251,8343,8463,8489,8554,8644,8713,8733,8854,8855,8863,8983,
9035,9037,9132,9164,9186,9221,9224,9252,9274,9404,9405,9433,9434,9470,
9470,9472,9489,9500,9585,9649),
diffdate=c(
826,431,302,306,698,393,368,1124,191,124,330,642,408,244,1001,391,246,
615,1118,539,612,245,813,516,1309,241,327,469,126,317,689,981,303,976),
dethdate=c(
8434,8304,NA,8414,8715,NA,8667,9142,8731,8750,8963,9120,9005,9028,9445,
9180,9189,9406,9711,9453,9465,9289,9640,9608,10010,9488,9523,9633,9667,
9547,9755,NA,9686,10084),
censdate=c(
NA,NA,8321,NA,NA,8519,NA,NA,NA,NA,NA,NA,NA,NA,NA,NA,NA,NA,NA,NA,NA,NA,
NA,NA,NA,NA,NA,NA,NA,NA,NA,10095,NA,NA))


cdcaids <- upData(cdcaids,
 labels=c(age     ='Age, y', infedate='Date of blood transfusion',
          diagdate='Date of AIDS diagnosis',
          diffdate='Incubation period (days from HIV to AIDS)',
          dethdate='Fictitious date of death',
          censdate='Fictitious censoring date'))


# Note that the style options listed with these
# examples are best suited for output to a postscript file (i.e., using
# the postscript function with horizontal=TRUE) as opposed to a graphical
# window (e.g., motif).


# To produce simple calendar event chart (with internal legend):
# postscript('example1.ps', horizontal=TRUE)
 event.chart(cdcaids,
  subset.c=c('infedate','diagdate','dethdate','censdate'),
  x.lab = 'observation dates',
  y.lab='patients (sorted by AIDS diagnosis date)',
  titl='AIDS data calendar event chart 1',
  point.pch=c(1,2,15,0), point.cex=c(1,1,0.8,0.8),
  legend.plot=TRUE, legend.location='i', legend.cex=1.0,
  legend.point.text=c('transfusion','AIDS diagnosis','death','censored'),
  legend.point.at = list(c(7210, 8100), c(35, 27)), legend.bty='o')


# To produce simple interval event chart (with internal legend):
# postscript('example2.ps', horizontal=TRUE)
 event.chart(cdcaids,
  subset.c=c('infedate','diagdate','dethdate','censdate'),
  x.lab = 'time since transfusion (in days)',
  y.lab='patients (sorted by AIDS diagnosis date)',
  titl='AIDS data interval event chart 1',
  point.pch=c(1,2,15,0), point.cex=c(1,1,0.8,0.8),
  legend.plot=TRUE, legend.location='i', legend.cex=1.0,
  legend.point.text=c('transfusion','AIDS diagnosis','death','censored'),
  x.reference='infedate', x.julian=TRUE,
  legend.bty='o', legend.point.at = list(c(1400, 1950), c(7, -1)))


# To produce more complicated interval chart which is
# referenced by infection date, and sorted by age and incubation period:
# postscript('example3.ps', horizontal=TRUE)
 event.chart(cdcaids,
  subset.c=c('infedate','diagdate','dethdate','censdate'),
  x.lab = 'time since diagnosis of AIDS (in days)',
  y.lab='patients (sorted by age and incubation length)',
  titl='AIDS data interval event chart 2 (sorted by age, incubation)',
  point.pch=c(1,2,15,0), point.cex=c(1,1,0.8,0.8),
  legend.plot=TRUE, legend.location='i',legend.cex=1.0,
  legend.point.text=c('transfusion','AIDS diagnosis','death','censored'),
  x.reference='diagdate', x.julian=TRUE, sort.by=c('age','diffdate'),
  line.by='age', line.lty=c(1,3,2,4), line.lwd=rep(1,4), line.col=rep(1,4),
  legend.bty='o', legend.point.at = list(c(-1350, -800), c(7, -1)),
  legend.line.at = list(c(-1350, -800), c(16, 8)),
  legend.line.text=c('age = 1', '       = 2', '       = 3', '       = 4'))


# To produce the Goldman chart:
# postscript('example4.ps', horizontal=TRUE)
 event.chart(cdcaids,
  subset.c=c('infedate','diagdate','dethdate','censdate'),
  x.lab = 'time since transfusion (in days)', y.lab='dates of observation',
  titl='AIDS data Goldman event chart 1',
  y.var = c('infedate'), y.var.type='d', now.line=TRUE, y.jitter=FALSE,
  point.pch=c(1,2,15,0), point.cex=c(1,1,0.8,0.8), mgp = c(3.1,1.6,0),
  legend.plot=TRUE, legend.location='i',legend.cex=1.0,
  legend.point.text=c('transfusion','AIDS diagnosis','death','censored'),
  x.reference='infedate', x.julian=TRUE,
  legend.bty='o', legend.point.at = list(c(1500, 2800), c(9300, 10000)))


# To convert coded time-to-event data, then, draw an event chart:
surv.time <- c(5,6,3,1,2)
cens.ind   <- c(1,0,1,1,0)
surv.data  <- cbind(surv.time,cens.ind)
event.data <- event.convert(surv.data)
event.chart(cbind(rep(0,5),event.data),x.julian=TRUE,x.reference=1)

Run the code above in your browser using DataCamp Workspace