PROC DMNEURL: Approximation to PROC NEURAL
parameter estimates. Here, the –MEAN–
variable contains the value for the optimization criterion and the
– STDEV– variable contains the accuracy value of the prediction.
which contains the predicted values (posteriors) and residuals for all observa-
tions in the DATA= input data set.
Variables of the output data set:
values of all ID variables
The following variables are added if a DECISION statement is used:
The number of observations in the OUT= data set agrees with that of the
DATA= input data set.
speciﬁes an output data set which is in structur identical to the OUT= output
data set but relates to the information given in the TESTDATA= input data set
rather than that of the DATA= input data set used in the OUT= output data set.
The number of observations in the TESTOUT= data set agrees with that of the
TESTDATA= input data set.
speciﬁes an output data set generated by PROC DMNEURL which contains
a number of ﬁt indices for each stage and for the ﬁnal model estimates. For
a binary target (response variable) it also contains the frequencies of the
additionally provided if a TESTDATA= input data set is speciﬁed.
Variables of the output data set:
– TARGET– (character) name of the target
– DATA– (character) speciﬁes the data set to which the ﬁt criteria correspond:
=TRAINING: ﬁt criteria belong to DATA= input data set =TESTDATA:
ﬁr criterai belong to TESTDATA= input data set
– TYPE– (character) describes type of observation
– TYPE–=– FITIND– for ﬁt indices;
– TYPE–=– ACCTAB– for frequencies of accuracy table (only for bi-
speciﬁes an output data set generated by PROC DMNEURL which contains all
eigenvalues and eigenvectors of the
matrix. When this option is speciﬁed,
this data set.
Variables of the OUTSTAT= output data set:
– TYPE– (character) type of observation
– EIGVAL– contains different numeric information
variables in the model; the ﬁrst variables correspond to CLASS
scaled. Note, that for nonbinary CLASS (nominal or ordinal categorical)
variables a set of binary dummy variables is created. In those cases the
preﬁx of variable names
used for a group of variables in the
data set may be the same for a successive group of variables which differs
only by a numeric sufﬁx.
Observations of the OUTSTAT= output data set:
1. The ﬁrst three observations, –TYPE–=–V–MAP– and –TYPE–=–C–MAP–,
contain the mapping indices between the variables used in the model and
the number of the variables in the data set. The –EIGVAL– variable
contains the number of index mappings. This is the same information
as in the ﬁrst observation of the OUTEST= data set, except that here
the –TYPE–=–EIGVAL– variables replaces the –TYPE–=–MEAN–
variable in the OUTEST= data set.
2. The –TYPE–=–EIGVAL– observation contains the sorted eigenvalues of
matrix. Here, the –EIGVAL– variable contains the eigen-
(OPTCRIT=SSE) optimization process.
See the document of PROC NLP
in SAS/OR for more details. Default is ABSGCONV=5e-4 in general and
ABSCONV=1e-3 for FUNCTION=EXP.
CORRDF : speciﬁes that the correct number of degrees of freedom is used for the
values of RMSE, AIC, and SBC. Without specifying CORRDF the error de-
grees of freedom are computed as
is the sum of weights
(if the WEIGHT statement is not used, each observation has a weight of 1 as-
is the total number of observations) and
is the number of
parameters. When CORRDF is speﬁﬁed the value
is replaced by the rank of
ing eigenvalues and eigenvectors compatible with the PRINCOMP procedure.
The COV and CORR options are valid only if an OUTSTAT= data set is speci-
ﬁed. If neither COV nor CORR are speciﬁed, the eigenvalues and eigenvectors
of the cross product matrix
are computed and written to the OUTSTAT=
is valid only for binary target. Values of
will enforce a better ﬁt of the
table. Note, that values for
which are far away from
will reduce the ﬁt
speciﬁes a cutoff threshold for deciding when a predicted value of a binary
response is classiﬁed as 0 or 1. The default is
, for observation
observation is counted in the ﬁrst column of the accuracy table (i.e. as 0),
otherwise it is counted in the second column (i.e. as 1). For nonbinary target
the cutoff= value is not used.
See the document of PROC NLP in SAS/OR for more details. Default is
FCRIT speciﬁes that the probability of the
test is being used for the selction of
principal components rather than the default
speciﬁes an upper bound for the number of components selected for predicting
Note, that the computer time and core memory will increase superlinear for