The HPDMDB Procedure

PROC HPDMDB Statement

PROC HPDMDB DATA= <libref.>SAS-data-set  <options> ;

The PROC HPDMDB statement invokes the procedure.

Required Arguments

DATA=<libref.>SAS-data-set

names the SAS data set that contains the information that you want added to the data mining database. If the data set resides on the SAS appliance, then the SAS appliance is used during summarization.

Optional Arguments

DMDBCAT=<libref.>SAS-catalog

names the metadata catalog to be created by PROC HPDMDB.

CLASSOUT=<libref.>SAS-data-set

names the data set to contain the summaries of classification variables that are specified in the CLASS statement.

VAROUT=<libref.>SAS-data-set

names the data set to contain the summaries of analysis variables that are specified in the VAR statement.

VARDEF=divisor

specifies the divisor to use in the calculation of the variance and standard deviation. Table 6.1 shows the possible values for divisor.

Table 6.1: Values for divisor

Value

Divisor

N

Number of observations ($n$)

DF (default)

Degrees of freedom ($n-1$)


PRINT

prints the class-level information to all open ODS destinations.

SPECIALMISSING

enables special missing values to be treated as separate levels.

MAXLEVEL=max

specifies the maximum number of levels to be reported for each class variable. If more than max levels of a class variable exist, PROC HPDMDB reports the frequency of unreported observations in a level named _OTHER_.