Re: st: generating age using dates

[Maarten buis <maartenbuis@yahoo.co.uk>]

--- On Fri, 17/12/10, martine etienne wrote:
> the dates look pretty normally distributed, 

It is not the shape of the distribution that is
relevant but the actual values. We cannot look at
them, and we don't know anything about your data,
but you should know the context and be able to 
look at these values and see if they are plausable.

> both variables are long format:
> survey_date 
>    long   %dD_m_Y   
>             
> q1_dob2     
>    long   %td   

When storing dates, that is done in years or weeks 
or quarters or... since some fixed date. You need to 
make sure that both variables use the same unit. The 
fact that one variable is in %dD_m_Y  and the other 
in %td suggest that this might be the problem. Take a 
look at the exact numerical values of these variables
(i.e. not the dates but the numbers).

Look at -help dates- for different conversion tools
to move one date type to another.

Hope this helps,
Maarten

--------------------------
Maarten L. Buis
Institut fuer Soziologie
Universitaet Tuebingen
Wilhelmstrasse 36
72074 Tuebingen
Germany

http://www.maartenbuis.nl
--------------------------


      

*
*   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/