Evaluation of a New Edit Methodology for the Common Core of Data Nonfiscal Surveys

• Activity Number: 607
• Type: Contributed
• Date/Time: Wednesday, August 7, 2013 : 2:00 PM to 3:50 PM
• Sponsor: Survey Research Methods Section
• Author(s): Elizabeth Goldberg*+ and Robert Stillwell and Jeffrey Little
• Companies: US Census Bureau and National Center for Education Statistics and US Census Bureau
• Keywords: data editing ; ratio edits ; historical data ; multivariate edits

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. The principal users of CCD nonfiscal data are the federal government, the education research community, state and local government officials, including school boards and LEA administrators; and the general public. With the 2010-11 survey year, public concerns were raised about the potential for extreme erroneous results to not be flagged in the editing process. As a result, a new methodology of editing based on comparing multiple years of data for an edited data element vs. the current year/prior year editing process previously used. This paper discusses the results of this new edit methodology on the data quality for the 2011-12 CCD survey year, as well as the potential for this method to be applied in other ways moving forward.