User Guide
103
Data Preparati
on
To sort the variable list to display all variables with unlabeled values at the top of
the list:
E Click the Unlabeled column heading under Scanned Variable List.
You can also s
ort by variable name or measurement level by clicking the
corresponding column heading under Scanned Variable List.
Value Label
Grid
Label. Dis
plays any value labels that have already been defined. You can add or
change labels in this column.
Value. Unique values for each selected variable. This list of unique values is
based on the number of scanned cases. For example, if you scanned only the
first 100 c
ases in the data file, then the list reflects only the unique values present
in those cases. If the data file has already been sorted by the variable for which
you want to assign value labels, the list may display far fewer unique values
than are ac
tually present in the data.
Count. Th
e number of times each value occurs in the scanned cases.
Missing.
Values defined as representing missing data. You can change the missing
values designation of the category by clicking the check box. A check indicates
that the category is defined as a user-missing category. If a variable already has a
range of v
alues defined as user-missing (for example, 90-99), you cannot add or
delete missing values categories for that variable with Define Variable Properties.
You can use the Variable view of the Data Editor to modify the missing values
categor
ies for variables with missing values ranges. For more information, see
“Missing Values” in Chapter 5 on p. 85.
Changed. Indicates that you have added or changed a value label.
Note:If
you specified 0 for the number of cases to scan in the initial dialog box, the
Value Label grid will initially be blank, except for any preexisting value labels and/or
defined missing values categories for the selected variable. In addition, the
Suggest
button f
or the measurement level will be disabled.
Measurement Level. Value labels are primarily useful for categorical (nominal
and ordinal) variables, and some procedures treat categorical and scale variables
differ
ently; so, it is sometimes important to assign the correct measurement level.
However, by default, all new numeric variables are assigned the scale measurement