Modified Statistical Process Control Techniques as an Edit Method for the Common Core of Data

• Activity Number: 75
• Type: Contributed
• Date/Time: Sunday, August 3, 2014 : 4:00 PM to 5:50 PM
• Sponsor: Government Statistics Section
• Author(s): Elizabeth Goldberg*+
• Companies: U.S. Census Bureau
• Keywords: edit ; statistical process control ; education

Abstract

The Common Core of Data (CCD) nonfiscal surveys consist of data submitted annually to the National Center for Education Statistics (NCES) by state education agencies (SEAs) in the 50 states, territories, and other agencies. CCD survey staff edits the data to produce a clean data file, which NCES uses to construct general-purpose publications and specialized reports. Beginning with the 2011-12 survey year, a new methodology of editing was implemented in the CCD. This method compared multiple years of data for an edited data element and is referred to as the "multiyear edits". Previously, current year data were only edited against the prior year in the CCD. This paper extends that work by comparing more classic statistical process control techniques to the multiyear method. This paper presents the details of the implementation, as well as several examples and results. Also, the paper discusses the issues and challenges involved in the application of these manufacturing based techniques to a large establishment survey.