The ROBUSTREG Procedure

ODS Table Names

The ROBUSTREG procedure assigns a name to each table that it creates. You can specify these names when using the Output Delivery System (ODS) to select tables and create output data sets. These names are listed in Table 98.11.

Table 98.11: ODS Tables Produced by PROC ROBUSTREG

ODS Table Name

Description

Statement

Option

BestEstimates

Best final estimates for LTS

PROC

SUBANALYSIS

BestSubEstimates

Best estimates for each subgroup

PROC

SUBANALYSIS

BiasTest

Bias test for MM estimation

PROC

BIASTEST

ClassLevels

Classification variable levels

CLASS

Default

CorrB

Parameter estimate correlation matrix

MODEL

CORRB

CovB

Parameter estimate covariance matrix

MODEL

COVB

CStep

C-step for LTS fitting

PROC

SUBANALYSIS

DependenceEquations

Design dependence equations

MODEL

LEVERAGE

Diagnostics

Outlier diagnostics

MODEL

DIAGNOSTICS

DiagSummary

Summary of the outlier diagnostics

MODEL

Default

DroppedComponents

Coefficients for MCD-dropped components

MODEL

LEVERAGE (OPC)

GoodFit

R square, deviance, AIC, and BIC

PROC

METHOD=

InitLTSProfile

Profile for initial LTS estimate

PROC

METHOD=

InitSProfile

Profile for initial S estimate

PROC

METHOD=

IterHistory

Iteration history

PROC

ITPRINT

LTSEstimates

LTS parameter estimates

PROC

METHOD=

LTSLocationScale

Location and scale for LTS

PROC

METHOD=

LTSProfile

Profile for LTS estimator

PROC

METHOD=

LTSRsquare

R square for LTS estimate

PROC

METHOD=

MCDDependenceEquations

Robust dependence equations

MODEL

LEVERAGE

MCDProfile

MCD profile

MODEL

LEVERAGE (MCDINFO)

MCDCenter

MCD center estimate

MODEL

LEVERAGE (MCDINFO)

MCDCov

MCD covariance estimate

MODEL

LEVERAGE (MCDINFO)

MCDCorr

MCD correlation estimate

MODEL

LEVERAGE (MCDINFO)

MMProfile

Profile for MM estimator

PROC

METHOD=

ModelInfo

Model information

MODEL

Default

NObs

Observations summary

PROC

Default

ParameterEstimates

Parameter estimates

MODEL

Default

ParameterEstimatesF

Final weighted LS estimates

PROC

FWLS

ParameterEstimatesR

Reduced parameter estimates

TEST

Default

ParmInfo

Parameter indices

MODEL

Default

SProfile

Profile for S estimator

PROC

METHOD=

Groups

Groups for LTS fitting

PROC

SUBANALYSIS

SummaryStatistics

Summary statistics for model variables

MODEL

Default

Tests

Results for tests

TEST

Default