Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
st: strange merge report
From
"Gregory, Christian" <[email protected]>
To
<[email protected]>
Subject
st: strange merge report
Date
Wed, 17 Nov 2010 09:53:26 -0500
Stata Colleagues,
I'm getting a strange merge report when I merge two datasets that I'm using. One data set has regional variables; the other is the CPS. The merge report says that none of the observations have been merged, but when I tabulate _merge, it shows that all of observations have been matched. Additionally, a check of the existence and means of the merge variables confirms that they are not in the data set before the merge, and they are after the merge.
In what follows, the CPS is the master data.
One version of the report is:
------------------
sort geogroup year
capture drop _merge
merge m:1 geogroup year using geodata
Result # of obs.
-----------------------------------------
not matched 0
matched 0 (_merge==3)
-----------------------------------------
. tab _merge
_merge | Freq. Percent Cum.
------------------------+-----------------------------------
matched (3) | 92,234 100.00 100.00
------------------------+-----------------------------------
Total | 92,234 100.00
----------------------------
Another version is
-------------------------------
sort geogroup year
capture drop _merge
merge m:1 geogroup year using geodata
Result # of obs.
-----------------------------------------
not matched .
from master . (_merge==1)
from using . (_merge==2)
matched . (_merge==3)
-----------------------------------------
. tab _merge
_merge | Freq. Percent Cum.
------------------------+-----------------------------------
matched (3) | 92,234 100.00 100.00
------------------------+-----------------------------------
Total | 92,234 100.00
--------------------------------------------
The practical effect of this is unclear: my estimates do vary a little from iteration to iteration, and I suspect this has something to do with this report.
Any help would be most appreciated.
Christian A. Gregory
Research Economist
Economic Research Service, USDA
1800 M. St. NW, Room S2095
Washington, DC 20036
202-694-5132
Christian A. Gregory
Research Economist
Economic Research Service, USDA
1800 M. St. NW, Room S2095
Washington, DC 20036
202-694-5132
*
* 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/