Trond Petersen has written some papers on time aggregation bias, which is what
this sounds like, somewhere in the sociological methods journals. That might
be a place to start.
Quoting Stas Kolenikov <[email protected]>:
> Dear Statalisters,
>
> I have an annual study where people report their status (employed /
> unemployed). It is not always asked when the transition from one state
> to another had happened. What can I do to smartly (hm...) assign
> the initiating and terminating times? A simple thing to do is to
> take the middle of the interval as the time of change. A better thing
> might be to integrate out the missingness in the style of EM algorithm.
> Can anybody provide a reference to what can be / should be / sometimes
> is done?
>
> --- Stas Kolenikov
> -- Ph.D. student in Statistics at UNC-Chapel Hill
> - http://www.komkon.org/~tacik/ -- [email protected]
>
> * This e-mail and all attachments to it are not intended to provide any
> * reasonable point of view and was transmitted to you in error. It
> * should be immediately deleted by all recepients unless they really
> * enjoy communicating with the author :). Other restrictions apply.
>
> *
> * 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/
>
*
* 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/
