st: Data manipulation with long datasets

[Sara Mottram <s.mottram@cphc.keele.ac.uk>]

Hi,

I am trying to follow the faqs "How do I analyze multiple failure-time 
data using Stata" (Cleves, 1999) to analyze some data concerning 
consultation with a family doctor. I think that I need to follow the 
Andersen and Gill model in section 3.2.1 for what I would like to do. 
The means that the data need to be in the form:

     | id     group   time0   time   status   number   size |
     |------------------------------------------------------|
     |  1   placebo       0      1        0        1      3 |
     |  2   placebo       0      4        0        2      0 |
     |  3   placebo       0      7        0        1      0 |
     |  4   placebo       0     10        0        5      0 |
     |  5   placebo       0      6        1        4      0 |
     |------------------------------------------------------|
     |  5   placebo       6     10        0        4      0 |
     |  6   placebo       0     14        0        1      0 |
     |  7   placebo       0     18        0        1      0 |
     |  8   placebo       0      5        1        1      3 |
     |  8   placebo       5     18        0        1      3 |
     |------------------------------------------------------|
     |  9   placebo       0     12        1        1      1 |
     |  9   placebo      12     16        1        1      1 |
     |  9   placebo      16     18        0        1      1 |
     +------------------------------------------------------+
My data are currently in long form with multiple consultations per 
person and a date for each of these consultations (which I have 
converted to an edate to allow calculations). I can easily make the date 
of the consultation representative of the 'time' variable in the example 
(by subtracting the start time of the study from the consultation date) 
but I cannot work out how to create an equivalent to the 'time0' 
variable where I need the time variable from the preceding row to become 
time0. I thought I might need some sort of within person command but I 
am struggling to find anything like this.

My data look like this, where duplicate_pp is the number of the 
consultation in the particular individual:

id    cons_dt      duplicate_pp
26    05 Jun 00    1
26    18 Aug 00    2
26    13 Oct 00    3
26    10 Nov 00    4
26    25 May 01    5
26    13 Jun 01    6
26    16 Jun 01    7
26    28 Jun 01    8
26    23 Oct 01    9
26    20 Nov 01    10
74    21 Dec 01    1
74    15 Jan 02    2
74    29 Jan 02    3
86    30 Mar 00    1
86    27 Apr 00    2
86    05 May 00    3
86    14 Jun 00    4
86    05 Feb 02    5

Could anyone help me out with creating the time0 variable please?
Thanks
Sara

--
Sara Mottram	
Research Assistant: Biostatistics
Primary Care Musculoskeletal Research Centre
Primary Care Sciences
Keele University
Staffordshire, ST5 5BG
Tel:  01782 584711
Fax:  01782 583911 
*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/