01-24-2017 02:06 PM
I'm dealing with a data cleaning problem. We only have Base SAS but I need to find a systematic way of cleaning a list of names and addresses eliminating duplicates.
The data has been entered over years with no control of how information was entered. For example, company names might be slightly changed and addresses entered any way someone wishes.
At present the data is manually cleaned but each time new data comes in it has to be cleaned again.
I've used so called merge purge programs in the past to clean mailing lists.
01-24-2017 03:39 PM
I like the solution from FriedEgg here:
Given your situation and the lack of Data Quality software, I would recommend getting either SAS Data Flux, or creating your own custom program. The link above is a starting point. Also, look at Link King, which has the SAS code available.