CENTER FOR EDUCATION STATISTICS
OFFICE OF EDUCATIONAL RESEARCH AND IMPROVEMENT 
U.S. DEPARTMENT OF EDUCATION


CHECKLIST 
DATA TAPE PREPARATION

             

                       
                                                     
A. Data set names give the survey system, component, year and version.      
                                                     
B Standard Definitions                                            
                                                     
  1.   FIPS Standards are used where applicable.                          
  2. CES standard definitions and codes are used where applicable.        
                                                     
C. Data Element Conventions                                          
                                                     
  1.   Numeric fields contain only numbers, zeros or missing values. 
2. Zeros are represented by "W". Do not use a "-" or blank. 
3.   Suppression symbols are removed from numeric fields and stored in associated "flag" fields.
   
  4. Negative numbers are represented in standard (IBM) signed numeric format.    
  5. When practical, numeric data fields containing continuous variables should be identical in length.  
  6. Separate record locations are used for all data items.              
                                                     
D. Record Conventions                                              
                                                     
  1. Rectangular structures are used, where possible. 2. Single record type is used.                      
  3. Logical record lengths are constant.                            
  4. Each record contains a unique identifier such as ID.                  
                                                     
E. Record Layout                                                
                                                     
  1. Record layout, location and format are documented. 2. Blocking factors and block size are documented. 3. _Record counts are included.                    
  4. Each record type is identified.                                
                                                     
F. Tape Format                                                  
                                                     
  1. 9 track, EBCDIC, 6250 BPI standard label tapes are used. 2. Standard alphanumeric characters are used.          
  3. Binary or packed decimal fields are avoided unless required by the size of the file or other factors.
                                                     
G.   Quality Control Procedures                                      
                                                     
  1. Record counts and totals are consistent between preliminary files and the final released tapes or explanations are included in the documentation.
  2. Internal inconsistencies are corrected or documented.                
  3. Major inconsistencies between current and past data are resolved or documented.  
  4. Imputed data are flagged.                                    
  5. Flags are consistently positioned within a file.   e            
  6.   Codes for missing, refused and non-applicable data are consistent within a survey or survey system.    
  7. All necessary steps have been taken to protect the confidentiality of respondents.