Re: st: Coding for multiple visits data

[Joerg Luedicke <joerg.luedicke@gmail.com>]

On Fri, Apr 8, 2011 at 8:16 PM, Tasha Amin <tamin_wh@hotmail.com> wrote:
> A case is someone who has TWO successive study visits with 0 RNA. However, the way the data is currently coded means the person's entire case history is 1 or 0, instead of just at the visit when the person transitions.I'm including the data again, to indicate how ID 1 should be case=0 till visit 5 with visit 6 being case=1. That is, person 1 is a non-case till visit 6, when he changes.
> Looks like:
> ID visit RNA case
> 1 1 1 1
> 1 3 1 1
> 1 5 0 1
> 1 6 0 1
> 1 7 0 1
> 2 1 1 0
> 2 2 1 0
> 2 3 1 0
> 2 4 1 0
>
> Want it to look like:
> ID visit RNA case
> 1 1 1 0
> 1 3 1 0
> 1 5 0 1
> 1 6 0 1
> 1 7 0 1
> 2 1 1 0
> 2 2 1 0
> 2 3 1 0
> 2 4 1 0

What you write is indeed not matching your desired outcome as
indicated by your second data example. Two successive zeros in RNA
would mean that visits 6 and 7 were flagged, but not 5 as in your
example. For instance:

. clear all

. input ID visit RNA case

ID      visit        RNA       case
1. 1 1 1 0
2. 1 3 1 0
3. 1 5 0 1
4. 1 6 0 1
5. 1 7 0 1
6. 2 1 1 0
7. 2 2 1 0
8. 2 3 1 0
9. 2 4 1 0
10. end

.
. gen case2=0

. bys ID (visit): replace case2=1 if RNA==0&RNA[_n-1]==0
(2 real changes made)

. list

+---------------------------------+
ID   visit   RNA   case   case2
---------------------------------
1.   1       1     1      0       0
2.   1       3     1      0       0
3.   1       5     0      1       0
4.   1       6     0      1       1
5.   1       7     0      1       1
---------------------------------
6.   2       1     1      0       0
7.   2       2     1      0       0
8.   2       3     1      0       0
9.   2       4     1      0       0
+---------------------------------+

However, I still do not know if that is what you want.

J.

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/