stset error: length[_n-1]==length

[Jesus Pulido]

Dear Statalist users,

I am running a conditional risk set model (time from previous event) for the time to adoption of a technology using Stata IC 15.1.

I have a dataset with multiple failures per subject. The period of observation is 2000-2017, with subjects entering the risk set at different years (i.e. not everyone became aware of the technology at t=0)

I initially used stset as follows:

stset length, fail(event==1) exit(time .)

failure event: event == 1
obs. time interval: (0, length]
exit on or before: time .

------------------------------------------------------------------------------
2,355 total observations
0 exclusions
------------------------------------------------------------------------------
2,355 observations remaining, representing
2,094 failures in single-record/single-failure data
4,963 total analysis time at risk and under observation
at risk from t = 0
earliest observed entry t = 0
last observed exit t = 17

But then I realized I needed to modify the stset instruction to allow for multiple failures per subject:

stset length, fail(event==1) enter(time0) exit(time .) id(idd)

id: idd
failure event: event == 1
obs. time interval: (length[_n-1], length]
enter on or after: time time0
exit on or before: time .

------------------------------------------------------------------------------
2,355 total observations
1,803 multiple records at same instant PROBABLE ERROR
(length[_n-1]==length)
------------------------------------------------------------------------------
552 observations remaining, representing
467 subjects
308 failures in multiple-failure-per-subject data
2,789 total analysis time at risk and under observation
at risk from t = 0
earliest observed entry t = 0
last observed exit t = 17

I don't understand how to fix this PROBABLE ERROR. Perhaps I can attribute this to some subjects failing every single year (e.g. subject i adopted technology in year 2001, then again in 2002, then again in 2003). But I am unsure how to fix this problem.

My data looks as follows:

* Example generated by -dataex-. To install: ssc install dataex
clear
input int idd float(time0 length) byte(event interval)
 2 0 10 1  1
 2 0  1 1  2
 2 0  1 1  3
 2 0  1 1  4
 2 0  1 1  5
 2 0  1 1  6
 2 0  1 1  7
 2 0  1 1  8
 3 0 .5 1  1
 3 0  1 1  2
 3 0  1 1  3
 3 0  1 1  4
 3 0  1 1  5
 3 0  1 1  6
 3 0  1 1  7
 3 0  1 1  8
 3 0  1 1  9
 3 0  1 1 10
 3 0  1 1 11
 4 0  2 1  1
 4 0  1 1  2
 4 0  1 1  3
 4 0  1 1  4
 4 0  1 1  5
 5 0  6 0  1
 6 0  3 1  1
 6 0  1 1  2
 6 0  1 1  3
 6 0  1 1  4
 7 0  5 1  1
 7 0  1 1  2
 7 0  1 1  3
 7 0  1 1  4
 7 0  1 1  5
 7 0  1 1  6
 7 0  1 1  7
 8 0 .5 1  1
 8 0  1 1  2
 8 0  1 1  3
 8 0  1 1  4
 8 0  1 1  5
 8 0  1 1  6
 8 0  1 1  7
 8 0  1 1  8
 8 0  1 1  9
 8 0  1 1 10
 8 0  1 1 11
 8 0  1 1 12
 9 0  5 1  1
 9 0  1 1  2
 9 0  1 1  3
 9 0  1 1  4
10 0 .5 1  1
10 0  1 1  2
10 0  1 1  3
10 0  1 1  4
10 0  1 1  5
10 0  1 1  6
10 0  1 1  7
11 0  3 1  1
11 0  1 1  2
11 0  1 1  3
11 0  1 1  4
11 0  1 1  5
11 0  1 1  6
11 0  1 1  7
11 0  1 1  8
11 0  1 1  9
12 0  2 1  1
12 0  1 1  2
12 0  1 1  3
12 0  1 1  4
12 0  1 1  5
12 0  1 1  6
13 0 .5 1  1
13 0  1 1  2
13 0  1 1  3
13 0  1 1  4
14 0 14 1  1
14 0  1 1  2
14 0  1 1  3
14 0  1 1  4
15 0  9 1  1
15 0  1 1  2
15 0  1 0  3
16 0  3 1  1
16 0  1 1  2
16 0  1 1  3
16 0  1 1  4
17 0 10 1  1
17 0  1 1  2
17 0  1 1  3
17 0  1 1  4
17 0  1 1  5
17 0  1 1  6
17 0  1 1  7
18 0  5 1  1
18 0  1 1  2
18 0  1 1  3
18 0  1 1  4
end

Thanks.