Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

RE: st: Re: Re: how to calculate employment history - panel data


From   "Nick Cox" <n.j.cox@durham.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   RE: st: Re: Re: how to calculate employment history - panel data
Date   Fri, 29 May 2009 10:57:37 +0100

Thanks for the plug. These references may also be relevant: 

SJ-7-4  dm0033  . . . . . . Speaking Stata: Counting groups, especially
panels
        . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  N.
J. Cox
        Q4/07   SJ 7(4):571--581                                 (no
commands)
        discusses how to count panels through reduction commands
        or through tabulation commands and how to overcome
        problems that do not yield easily to these approaches

SJ-7-3  pr0033  . . . . . . . . . . . . . .  Stata tip 51: Events in
intervals
        . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  N.
J. Cox
        Q3/07   SJ 7(3):440--443                                 (no
commands)
        tip for counting or summarizing irregularly spaced
        events in intervals

Nick 
n.j.cox@durham.ac.uk 

Martin Weiss

I hope you can take it from here, with the added help of Nick`s
http://www.stata-journal.com/article.html?article=dm0029

go.diva@web.de

First of all thanks a lot! It is definitely a good start. 

But, if I set in your code the window instead of "begin-6" to a longer
period, say "begin-31" than the window will be overwritten by the
previous
employment spells. In addition, it also does not count the number of
weeks
correctly until a previous emloyment spells starts.

Does somebody see a solution to the problem?  

From: "Martin Weiss" <martin.weiss1@gmx.de>

> -egen- happily accepts expressions for some of its functions, so let`s
try

> and use that...
>
> ***
>
> clear*
>
> input Id   spell  begin  end     status:mylabel , auto
> 1    1       12        14       empl
> 1    2       15         46      unempl
> 1    3       47         52      sick
> 1    4       59         66      unempl
> 1    5       70         80      empl
> 1    6       81         88      unempl
> 1    7       89        105     empl
> 2    1       14         21      unempl
> 2    2       55         59      sick
> 2    3       61        109     empl
> 2    4      110       115     unempl
> 2    5      116       200     empl
> end
> compress
>
> bys Id: gen byte newspell=sum((status[_n-1]==1)*(_n!=1))
> bys Id newsp: egen window=total((begin-6)*(_n==_N)*(_n!=1))
> bys Id newsp: /*
> */egen weeks=total((status==2)*/*
> */(begin<=window)*(end>=window)*/*
> */(end-window))
> l, sepby(Id news)
> ***

> From: <go.diva@web.de>

>> I have the following panel dataset:
>>
>> Id   spell  begin  end            status
>> 1    1       12        14              empl
>> 1    2       15         46             unempl
>> 1    3       47         52             sick
>> 1    4       59         66             unempl
>> 1    5       70         80             empl
>> 1    6       81         88             unempl
>> 1    7       89        105            empl
>> 2    1       14         21             unempl
>> 2    2       55         59             sick
>> 2    3       61        109            empl
>> 2    4      110       115            unempl
>> 2    5      116       200            empl
>>
>>
>> I want now to calculate for each spell and person how many weeks the 
>> person has been e.g. unemployed during the past 31 weeks (6 month)
when 
>> he/she enters employment.
>>
>> The problem is not to calculate the entire weeks spent in
unemployment 
>> but only the number of weeks during a fixed period of time.

*
*   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/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index