fitdistrplus (version 1.1-6)

Surv2fitdistcens: Handling of data formated as in the survival package for use in fitdistcens()

Description

Provide a function to prepare a data frame needed by fitdistcens() from data classically coded when using the Surv() function of the survival package

Usage

Surv2fitdistcens(time, time2, event,
                      type=c('right', 'left', 'interval', 'interval2'))

Arguments

time

for right censored data, this is the follow up time. For interval data, the first argument is the starting time for the interval.

event

The status indicator, normally 0=alive, 1=dead. Other choices are TRUE/FALSE (TRUE = death) or 1/2 (2=death). For interval censored data, the status indicator is 0=right censored, 1=event at time, 2=left censored, 3=interval censored. For factor data, assume that it has only two levels with the second level coding death.

time2

ending time of the interval for interval censored. Intervals are assumed to be open on the left and closed on the right, (start, end].

type

character string specifying the type of censoring. Possible values are "right", "left", "interval", "interval2".

Value

Surv2fitdistcens returns a data.frame with two columns respectively named left and right.

Details

Surv2fitdistcens makes a data.frame with two columns respectively named left and right, describing each observed value as an interval as required in fitdistcens(): the left column contains either NA for left-censored observations, the left bound of the interval for interval-censored observations, or the observed value for non-censored observations. The right column contains either NA for right-censored observations, the right bound of the interval for interval censored observations, or the observed value for non-censored observations.

References

Delignette-Muller ML and Dutang C (2015), fitdistrplus: An R Package for Fitting Distributions. Journal of Statistical Software, 64(4), 1-34.

See Also

See fitdistrplus for an overview of the package. See fitdistcens for fitting of univariate distributions to censored data and fremale for the full dataset used in examples below. See Surv for survival objects which use the same arguments.

Examples

# NOT RUN {
# (1) randomized fictive survival data - right-censored
#
origdata <- data.frame(rbind(
c(   43.01, 55.00,     0),
c(   36.37, 47.17,     0),
c(   33.10, 34.51,     0),
c(   71.00, 81.15,     1),
c(   80.89, 81.91,     1),
c(   67.81, 78.48,     1),
c(   73.98, 76.92,     1),
c(   53.19, 54.80,     1)))
colnames(origdata) <- c("AgeIn", "AgeOut", "Death")

# add of follow-up time (for type = "right" in Surv())
origdata$followuptime <- origdata$AgeOut - origdata$AgeIn
origdata

### use of default survival type "right"
# in Surv()
survival::Surv(time = origdata$followuptime, event = origdata$Death, type = "right")
# for fitdistcens()
Surv2fitdistcens(origdata$followuptime, event = origdata$Death, type = "right")

# use of survival type "interval" 
# in Surv()
survival::Surv(time = origdata$followuptime, time2 = origdata$followuptime, 
          event = origdata$Death, type = "interval")
# for fitdistcens()
Surv2fitdistcens(time = origdata$followuptime, time2 = origdata$followuptime, 
          event = origdata$Death, type = "interval") 

# use of survival type "interval2" 
origdata$survivalt1 <- origdata$followuptime
origdata$survivalt2 <- origdata$survivalt1
origdata$survivalt2[1:3] <- Inf
origdata
survival::Surv(time = origdata$survivalt1, time2 = origdata$survivalt2, 
type = "interval2")
Surv2fitdistcens(origdata$survivalt1, time2 = origdata$survivalt2, 
                type = "interval2")


# (2) Other examples with various left, right and interval censored values
#
# with left censored data
(d1 <- data.frame(time = c(2, 5, 3, 7), ind = c(0, 1, 1, 1)))
survival::Surv(time = d1$time, event = d1$ind, type = "left")
Surv2fitdistcens(time = d1$time, event = d1$ind, type = "left")

(d1bis <- data.frame(t1 = c(2, 5, 3, 7), t2 = c(2, 5, 3, 7), 
  censtype = c(2, 1, 1, 1)))
survival::Surv(time = d1bis$t1, time2 = d1bis$t2, 
  event = d1bis$censtype, type = "interval")
Surv2fitdistcens(time = d1bis$t1, time2 = d1bis$t2, 
  event = d1bis$censtype, type = "interval")

# with interval, left and right censored data
(d2 <- data.frame(t1 = c(-Inf, 2, 3, 4, 3, 7), t2 = c(2, 5, 3, 7, 8, Inf)))
survival::Surv(time = d2$t1, time2 = d2$t2, type = "interval2")
Surv2fitdistcens(time = d2$t1, time2 = d2$t2, type = "interval2")

(d2bis <- data.frame(t1 = c(2, 2, 3, 4, 3, 7), t2 = c(2, 5, 3, 7, 8, 7), 
  censtype = c(2,3,1,3,3,0)))
survival::Surv(time = d2bis$t1, time2 = d2bis$t2, 
  event = d2bis$censtype, type = "interval")
Surv2fitdistcens(time = d2bis$t1, time2 = d2bis$t2, 
  event = d2bis$censtype, type = "interval")

# }