UPCOMING WEBINAR: From Thousands of Tables To One Clear Story: using AI in survey analysis When Displayr imports a data file, it will, from time-to-time, automatically create variables that are not in the original data file. This will occur due to:
- Automatic correction of errors.
- Variables being shared between Multiple Response Sets created within the SPSS file.
Identifying variables created by Displayr
Variables created by Displayr (as well as new variables created by users) have an editable Name in Properties under General > General.
Whereas, variables that exist in the raw data file have their Name greyed out:
Scenarios when Displayr automatically creates variables
Automatic correction of errors
When importing a data file, Displayr automatically scans for common problems in data files and automatically fixes these. Sometimes the fix involves creating new variables and hiding variables in the data file. Once you have gotten your data into Displayr, it is necessary to check that the data is all as you expect. This is typically something of a never-ending process, but the following basic checks are the minimum:
- Sample size
- Checking that the file only contains completed interviews
- Grouping of variables into variable sets
Overlapping SPSS Multiple Response Sets
You can create a special structure in SPSS called a Multiple Response Set, which groups together individual variables into a set for analysis in SPSS. In SPSS, one variable can appear in multiple Multiple Response Sets. Displayr will honor any Multiple Response Sets existing in the file and set their variable set Structure to Binary-Multi on import. However, Displayr only permits a variable to be a part of a single Multiple Response Sets (and a variable set for that matter). Thus, if the SPSS data file indicates a variable appears in multiple Multiple Response Sets, Displayr makes additional copies of the variable to use in the additional variable sets. The only way to avoid this from occurring is to modify the original SPSS data file.