Introduction
Similarity Analysis
The SIMILARITY procedure computes similarity measures associated with time-stamped data, time series, and other sequentially ordered numeric data. The SIMILARITY procedure includes the following features:
ability to accumulate time-stamped data into a time series
missing value interpretation
zero value interpretation
-
functional transformations of time series, including the following:
log (LOG)
square-root (SQRT)
logistic (LOGISTIC)
Box-Cox (BOXCOX)
user-defined transformations
simple differencing and seasonal differencing
time series missing value trimming
time warping by compressing or expanding the input sequence with respect to the target sequence
-
sequence normalizations, including the following:
standard (STANDARD)
absolute (ABSOLUTE)
user-defined normalizations
-
sequence scaling, including the following:
standard (STANDARD)
absolute (ABSOLUTE)
user-defined scaling
-
ability to compute similarity measures, including the following:
squared deviation (SQRDEV)
absolute deviation (ABSDEV)
mean square deviation (MSQRDEV)
mean absolute deviation (MABSDEV)
user-defined similarity measures
-
sliding similarity measures analysis with three types of sequence sliding:
no sliding
slide by time index
slide by season index
support for large data sets