Dear Martin,
Thank you very much for the advice! This last solution definitely produces stable results so solves the problem of outcome variation. I am still designing a way to ensure the code deals correctly with my numerous instances of tied data but so far it seems to work.
Thanks a lot again!
warm regards,
Ekaterina
In message <000b01ca3947$39d063a0$ad712ae0$@[email protected]> [email protected] writes:
>
> <>
>
> " Out of this dataset I want to keep for each individual the date he or she
> made his first approach and the date he or she was first accepted."
>
>
> Ekaterina might also want to try -collapse- for this problem setup:
>
>
> *************
> clear*
>
> inp byte id /*
> */ str20(dateapproached dateaccepted )
> 1 "20.04.2007" " "
> 1 "20.04.2007" " "
> 1 "18.05.2007" "20.05.2007"
> 1 "18.05.2007" " "
> 2 "19.01.2006" " "
> 2 "20.03.2007" "24.03.2007"
> 2 "20.03.2007" " . "
> 3 "11.09.2007" "18.09.2007"
> 3 "11.09.2007" "15.09.2007"
> 3 "01.10.2007" " "
> 3 "07.11.2007" " "
> 4 "06.06.2007" " "
> 4 "08.07.2007" " "
> end
>
> replace dateaccepted= /*
> */ trim(dateaccepted)
>
> gen dateapproached2= /*
> */ date(dateapproached, "DMY")
> format dateapproached2 /*
> */ %tdMonth_DD,_CCYY
>
> gen dateaccepted2= /*
> */ date(dateaccepted, "DMY")
> format dateaccepted2 /*
> */ %tdMonth_DD,_CCYY
>
> drop dateapproached /*
> */ dateaccepted
>
> compress
> list, noobs sepby(id)
>
> collapse (first) dateapproached2 /*
> */ (firstnm) dateaccepted2, /*
> */ by(id)
>
> list, noobs
> *************
>
>
>
> HTH
> Martin
>
>
> -----Ursprüngliche Nachricht-----
> Von: [email protected]
> [mailto:[email protected]] Im Auftrag von Ekaterina
> Hertog
> Gesendet: Samstag, 19. September 2009 18:23
> An: [email protected]
> Betreff: st: How to generate a variable equalling an earliest date of action
> b y individual?
>
> Dear all,
> I have a dataset of individuals each of whom approaches a number of others
> and after approaching each person is either accepted or rejected. I would
> like to do an event history analysis of how the duration of time it takes
> for an individual to secure an acceptance depends on his or hers individual
> characteristics.
> The variables I am interested in have the following structure (missing
> dateacceppted means a rejection):
>
> id dateapproached dateaccepted
> 1 20.04.2007 .
> 1 20.04.2007 .
> 1 18.05.2007 20.05.2007
> 1 18.05.2007 .
> 2 19.01.2006 .
> 2 20.03.2007 24.03.2007
> 2 20.03.2007 .
> 3 11.09.2007 18.09.2007
> 3 11.09.2007 15.09.2007
> 3 01.10.2007 .
> 3 07.11.2007 .
> 4 06.06.2007 .
> 4 08.07.2007 .
>
> Out of this dataset I want to keep for each individual the date he or she
> made his first approach and the date he or she was first accepted.
> To do so I tried to create a new variable date1accept which for each
> individual has the same value => the date he or she was first accepted.
> After that I dropped all the observations, but the 1st one for each
> individual.
> To do so I used the following code:
> sort id dateaccept
> foreach X of new date1accept {
> by id : gen `X' = dateaccept[1]
> }
>
> sort id
> by id: gen y=_n
> keep if y==1
>
> I then ran two tests and Stata confirmed that thes assertions below were
> true:
> /*To check that all the values of date1accept are the same*/
> bysort id (date1accept) : assert date1accept[1] == date1accept[_N]
> /*To check that dat1accept = the lowest value of dateaccept*/
> bysort id (dateaccept) : assert dat1accept[1] == dateaccept[1]
>
> yet something seems to be wrong with my commands, each time I re-run the
> code it comes up with slightly different set of date1accept values. I cannot
> understand where can my code be wrong so my tests do not pick it up.
> Could anyone suggest what might be wrong or offer an alternative solution
> for my problem?
> I will be most grateful for any advice,
> Warm regards,
> Ekaterina
>
> *
> * 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/
>
>
> *
> * 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/
--
Ekaterina Hertog (nee Korobtseva)
Nissan Institute of Japanese Studies
27 Winchester Road, Oxford
OX2 6NA
*
* 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/
