| Brooke Ellen Delgoffe |
PRESENTATION ONLY
Contact information is likely one of the most common pieces of data collected. Methods for approaching address data in terms of missingness, typos, and standardization will be covered in order to help the reader to force this common source of messy data into a cleaner version. By fixing some of the common issues with the data you can alleviate some of the common downstream issues with returned mail and haphazard mapping, whilst learning about some helpful beginner topics like fuzzy matching, SASHELP library datasets, and error finding macros.
SAS 9.4
Brief Outline:
• Introduction
• Common Issues Found in Address Data
• Additional Issues that Arise with Historical Attribution
• Special Address Issues, Beware the Default!
• Ways to Identify Issues
o Invalid Names and Address Components
o Address Component Abbreviations
• Ways to Resolve Issues
o Standardizing Address Components
o Spelled Numbers vs. Numeric
o Common Misspellings |