Re: st: RE: RE: joinby command and memory issues

["Weichle, Thomas" <Thomas.Weichle@va.gov>]

Eric, I'm trying to apply the second method that you suggested because I
need to keep all the receipt dates.  After I reshape epo.dta, it creates
a dataset of 1 record per individual.  Here are my reshaped data
results.  36,381 individuals with a maximum of 854 dates.  Someone
received the EPO drug very often!  Now that I have 1 record per
individual, wouldn't it be appropriate to then do a 1:m (many) merge
instead of a joinby where the many represents each of the hemoglobin
test dates for the individual?  I believe the data are set up
appropriately for this 1:many merge.

reshape wide epo_dt, i(study_id) j(i)

Data                               long   ->   wide
------------------------------------------------------------------------
-----
Number of obs.                   278492   ->   36381
Number of variables                   4   ->     856
j variable (854 values)               i   ->   (dropped)
xij variables:
                                 epo_dt   ->   epo_dt1 epo_dt2 ...
epo_dt854
------------------------------------------------------------------------
-----

Tom Weichle
Math Statistician
Center for Management of Complex Chronic Care (CMC3)
Hines VA Hospital, Bldg 1, C202
708-202-8387 ext. 24261
Thomas.Weichle@va.gov 


*
*   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/