st: imputation of missing dates

[Yulia Blomstedt <sungurik@gmail.com>]

Dear Statalist,
I need to impute the missing data in a dataset by matching it to the
already existing data. I have never worked with either imputation or
matching and am at a loss. I would deeply appreciate any advice.
My dataset contains background data for individuals who participated
in a medical examination (i.e., “participants”) and who did not
participate in the examination (“non-participants”) between 1990-2006.
All individuals were invited to participate in the examination when
they reached a certain age. The examination usually took place during
the same year as they reached that age between mid-January and  the
end of June or between August and mid-December.
I have the following data: the year (yyyy) when the individuals were
invited to participate in the examination (YEAR) and the exact date
(yyyymmdd) when the “participants” have participated in the
examination (EXAMDATE).
I need to create an EXAMDATE for “non-participants”, the date when
they could have participated in the examination. How do I do it?
The EXAMDATE of “non-participants” should have the same
range/distribution as among the “participants”, i.e., it should be
between mid-January and the end of June or between August and
mid-December during the year when a “non-participant” was invited to
the examination.
Thank you in advance for your help.
Yulia

*
*   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/