> -----Original Message-----
> From: Stephen P. Jenkins [mailto:[email protected]]
> Sent: 22 May 2008 09:35
> To: '[email protected]'
> Subject: st: duration data: stock sampling
>
>
> >>>>>>>>>>>>
>
> Date: Wed, 21 May 2008 14:24:15 +0000
> From: marcel spijkerman <[email protected]>
> Subject: st: duration data: stock sampling
>
> Dear statalisters,
>
> I have a sample of duration data on unemployment. The sample
> shares characteristics of stock and flow sample selection.
> That is, I have all persons that where unemployed between 1
> january 1999 and 1 january 2007; including those who have
> been unemployed before 1 january 1999 and still unemployed
> between 1999 and 2007 as well as new entrants who became
> unemployed somewhere between 1999 and 2007.
>
> For estimation I use the specification of Jenkins for
> discrete duration data where spells are converted to spell
> months and estimating proceeds by estimation of binary data.
> My question is whether for those who were already unemployed
> before 1999, I should condition the likelihood as described
> by Jenkins. If so, how should I do this?
>
> <<<<<<<<<<<<<<
>
> You have a combination of sampling types: (i) inflow sample
> (spells begin within window of observation), and (ii) stock
> sample with follow-up (spells starting before window of
> observation and surviving until at least start of window). I
> assume you know when those in sample (ii) began their spell;
> if not, the spells are left-censored and you're stuck.
> Otherwise, yes, the likelihood contributions for those spells
> of type (ii) must use appropriate conditioning for "delayed
> entry" (a.k.a. "left truncation"), as described in my website
> materials and elsewhere.
>
>
> Stephen
> -------------------------------------------------------------
> Professor Stephen P. Jenkins <[email protected]>
> Director, Institute for Social and Economic Research
> University of Essex, Colchester CO4 3SQ, U.K.
> Tel: +44 1206 873374. Fax: +44 1206 873151.
> http://www.iser.essex.ac.uk
> Survival Analysis using Stata:
> http://www.iser.essex.ac.uk/teaching/degree/stephenj/ec968/
> Downloadable papers and software: http://ideas.repec.org/e/pje7.html
*
* 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/
