Also assuming that it's a one-to-one merge - if not the number of
observations would have increased. Also assuming that the OP has
specified the merge correctly - again the number of observations might
have increased if there's more than one merge in the -using- data.
I think it's best to start from scratch.
> Well, I don't think you should ever save the new merged dataset on top of
> the master (i.e., don't use -save, replace-). If you follow this advice
> then you could just -use master-. Assuming you didn't follow this advice,
> you can retrieve the master dataset (if you didn't specify -update- as an
> option). Just type:
>
> keep if _merge==1 | _merge==3
> drop _merge
>
> if the using dataset contains some variables not in the master dataset,
> you
> then drop those:
>
> drop usingvar1 usingvar2 usingvar3...
>
> Michael Blasnik
> [email protected]
>
> ----- Original Message -----
> From: "louis boakye-yiadom" <[email protected]>
> To: <[email protected]>
> Sent: Saturday, April 09, 2005 12:24 PM
> Subject: st: Retrieving a master dataset after merging
>
>
>> Dear All,
>> After doing a -merge-, can one retrieve the master dataset? If yes, how
>> can it be done? Thank you.
>>
>> Louis
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
