100
Chapter 6
Figure 6-1
Specifying missing values fora con tinuous variable
Reading inm ixed data. Note that when you a re reading in fields with numeric storage (either
integer, real, time, timestamp, or date), any non-numeric values are set to null or system missing.
This is because, unlike some applications, does not allow mixed storage types within a field. To
avoid this, any fields with mixed data should be read in as strings by changing the storage type in
the source node or external application as necessary.
Readingempty strin gs from Oracle. When reading fro m or writing to an Oracle database, be aware
that, unlike SPSS Modeler and unlike most other databases, Oracle treats and stores empty string
values as equivalent to null values. This means that the same data extracted from an Oracle
database may behave differently than when extracted from a file or another database, and the data
may return different results.
Handling Missing Values
Youshould decide how to treat missing value sin li ght of your business or domain knowledge. To
ease training time and increase accuracy, you may want to remove blanks from your data set. On
the other hand, the presence of blank values may lead to new business opportun ities or additional
insights. In choosing the best technique, you should conside r the following aspects of your data:
Size of the data set
Number of fields containing blanks
Amount of missing information