D.4  Shedding of Cytomegalovirus in HIV-Infected Individuals
=============================================================

Description of Variables:

id          patient ID
urineL      days of last negative shedding in urine since earliest urine shedding date 
urineR      days of first positive shedding in urine
bloodL      days of last negative shedding in blood since earliest blood shedding date
bloodR      days of first positive shedding in blood
urine.cens  shedding in urine status:
            0 if right censored; 2 if left censored; 3 if interval censored
blood.cens  shedding in blood status:
            0 if right censored; 2 if left censored; 3 if interval censored


References:

Betensky R and Finkelstein D (1999). 
A nonparametric maximum likelihood estimator for bivariate interval censored data. 
Statistics in Medicine, 18(22): 3089-3100.

Goggins W and Finkelstein D (2000). 
A proportional hazards model for multivariate interval-censored failure time data. 
Biometrics, 56(3): 940-943.


> cmvdata <- read.table("cmvdata.dat", header=T)

> dim(cmvdata)  
  [1] 232   7

> cmvdata[cmvdata$id %in% c(20116,20286,20309,70143,70897,140268,210066,210461),]

      id urineL urineR bloodL bloodR urine.cens blood.cens
   20116    346     NA    346     NA          0          0
   20286    264    300    350     NA          3          0
   20309    252    280    252    336          3          3
   70143     NA      1    166     NA          2          0
   70897     28     56     NA      1          3          2
  140268     NA     NA     NA     NA         NA         NA
  210066     NA      1    172    258          2          3
  210461     NA      1     NA      1          2          2