SCALEMIN Subcommand (SET command)
For IBM® SPSS® Statistics data files that were created prior to release 8.0 and data read from external sources, you can specify the minimum number of data values for a numeric variable that is used to classify the variable as continuous (scale) or nominal. Variables with fewer than the specified number of unique values are classified as nominal. All string variables are classified as nominal, regardless of the number of unique values.
There are numerous other conditions that are evaluated prior to applying the minimum number of data values rule when determining to apply the continuous (scale) or nominal measurement level. Conditions are evaluated in the order listed in the table below. The measurement level for the first condition that matches the data is applied.
| Condition | Measurement Level |
|---|---|
| Format is dollar or custom-currency | Continuous |
| Format is date or time (excluding Month and Wkday) | Continuous |
| All values of a variable are missing | Nominal |
| Variable contains at least one non-integer value | Continuous |
| Variable contains at least one negative value | Continuous |
| Variable contains no valid values less than 10,000 | Continuous |
| Variable has N or more valid, unique values* | Continuous |
| Variable has no valid values less than 10 | Continuous |
| Variable has less than N valid, unique values* | Nominal |
* N is the user-specified cut-off value. The default is 24.