Various useful tips and tricks can be found here:
http://blog.stata.com/2011/04/18/merging-data-part-1-merges-gone-bad/http://blog.stata.com/2011/05/27/merging-data-part-2-multiple-key-merges/
On Tue, Jan 29, 2013 at 2:26 PM, Richard Goldstein
<richgold@ix.netcom.com> wrote:
> Assuming you have some id variable, merge on that; there should be
> exactly 200 with _merge=3 so just keep those (maybe fastest if you make
> dataset2a with just the id variable(s)) as dataset1a (don't forget to
> drop _merge)
>
> Rich
>
> On 1/29/13 8:23 AM, Lars Folkestad wrote:
>> That was my idea too.
>> But how?
>>
>> lars
>>
>> Den 29/01/13 14.18 skrev "Richard Goldstein" <richgold@ix.netcom.com>:
>>
>>> why not just make a new data set (say "dataset1a") consisting only of
>>> the 200?
>>>
>>> Rich
>>>
>>> On 1/29/13 8:14 AM, Lars Folkestad wrote:
>>>> Dear List
>>>>
>>>> I have to data sets
>>>>
>>>> dataset1: Consists of 40 variables and 800 unique observations
>>>> (persons).
>>>> dataset2: consists of the same 40 variables and 200 randomly selected
>>>> from
>>>> dataset 1 entered to be able to check for concistancy in entry.
>>>>
>>>> All data are based on data from a questionnaire.
>>>>
>>>> I want to know if there are many mis matches.
>>>>
>>>> I am going to use the following command:
>>>>
>>>> .use dataset1, clear
>>>> .cf _all using dataset2, verbose
>>>>
>>>>
>>>>
>>>> But how do i get stata to only compare the 200 sets of questionnaire
>>>> data
>>>> that was double entered?
>>>>
>>>> Thank you
>>>>
>>>> Lars
> *
> * For searches and help try:
> * http://www.stata.com/help.cgi?search
> * http://www.stata.com/support/faqs/resources/statalist-faq/
> * http://www.ats.ucla.edu/stat/stata/
--
---------------------------------
Maarten L. Buis
WZB
Reichpietschufer 50
10785 Berlin
Germany
http://www.maartenbuis.nl
---------------------------------
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/faqs/resources/statalist-faq/
* http://www.ats.ucla.edu/stat/stata/
