st: Duration models: database preparation

[nanss@iscte.pt]

Hello

I know my question has an obvious response to some of you but I need  
some insights. I'm preparing a database from a survey in which  
individuals report their labour market status (employed, unemployed,  
inactive, ...). My intent is to prepare this database to estimate  
duration models on dismissed individuals and analye the influence of  
some institutional changes on the duration of the unemployment spells.

I've been reading the book from Cleves et al. "An introduction to  
Survival analysis using STATA" and the book from Colin Cameron and  
Pravin Trivedi.

My question is the following: are the two following ways to organize  
the data produce equal? After stset the first stabase, commands like  
streg produce the same results in each of this cases.

1)

id      date0            date1       event
1      05/05/2005       10/05/2005     1
1      11/05/2005       16/05/2005     1
1      17/05/2005       18/05/2005     2
2      05/05/2005       10/05/2005     1
2      11/05/2005       16/05/2005     2



2)

id      spell(days)       event
1          11                2
2          10                2


Best regards,

N�dia











*
*   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/