Re: st: How to drop individuals from sample?

[Nick Cox <njcoxstata@gmail.com>]

In addition, -egen- is happy with arguments such as -total(event ==  
1)-, so the code can be simplified by not creating an indicator  
variable.

Nick

On 25 Jul 2012, at 08:25, Maarten Buis <maartenlbuis@gmail.com> wrote:

> On Wed, Jul 25, 2012 at 8:54 AM, Dheepan Ratha Krishnan wrote:
> > I am looking for a stata
> > command that will enable me to exclude individuals who have
> > experienced a particular life event more than once in my dataset.
>
> That depends on how your data is structured. I will assume that the
> data has the following structure: Each event has its own record, so
> the same individual can have multiple records. The type of event is
> stored in a separate variable, for example:
>
> person event_date event_type other_vars
> 1         02Jan2012 married     ...
> 1         03Jan2012 divorced    ...
> 1         04Jan2012 married
> 2         01Feb1950 married    ...
> 2         01Jun2012 widowed ....
>
> In this case you would want to ignore person 1 as he married twice (in
> three days...). Typically you do not have the variable event_type as a
> string but as a numeric variable with labels attached. Say 1 is
> married 2 is divorced and 3 is widowed, and you are interested in the
> event married. Than you type:
>
> gen byte married = event == 1
> bys person : egen tot_married = total(married)
> drop married
>
> The variable tot_married counts the number of times a person got
> married, so you want to ignore all persons with tot_married > 2. So
> you add to any subsequent command the condition -if tot_married < 2-.
>
> This way you ignore the entire person 1, but say you want to use the
> first marriage of person 1 just not any subsequent marriages. Than you
> type:
>
> gen byte married = event == 1
> bys person (event_date) : gen tot_married = sum(married)
> drop married
>
> To read more about this see:
> http://www.stata.com/support/faqs/data-management/true-and-false/
> help egen
> help sum()
> help if
*
*   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/