Translation from Narrative Text to Standard Codes Variables with Stata

Abstract:     
This paper describes screening, a new Stata command for data-management that can be used to examine the content of complex narrative text variables to identify one or more user-defined keywords. Thus the command is particularly useful to deal with string data type contaminated with abbreviations and/or mistakes. Although the main duty of screening is identification, a rich set of options allow a direct translation from the original narrative string to a user-defined standard coding scheme. Moreover the command is flexible enough to facilitate the merging of information from different sources and to extract substring from the desired variable.

Number of Pages in PDF File: 20

Keywords: screening, keyword-matching, narrative text variables, standard coding schemes

JEL Classification: C81, C87, C88

working papers series