The COUNTREG Procedure

Functional Summary

Table 12.1 summarizes statements and that you can use in the COUNTREG procedure.

Table 12.1: PROC COUNTREG Functional Summary

Description

Statement

Option

Data Set Options

   

Specifies the input data set

COUNTREG

DATA=

Specifies the input spatial weights data set

COUNTREG

WMAT=

Specifies the identification variable for panel data analysis

COUNTREG

GROUPID=

Does not row-normalize the spatial weights matrix

COUNTREG

NONORMALIZE

Writes parameter estimates to an output data set

COUNTREG

OUTEST=

Requests that the procedure produce graphics via the Output Delivery System

COUNTREG

PLOTS=

Writes estimates to an output data set

OUTPUT

OUT=

Declaring the Role of Variables

   

Specifies BY-group processing

BY

 

Specifies classification variables

CLASS

 

Specifies a frequency variable

FREQ

 

Specifies a weight variable

WEIGHT

 

Specifies a spatial ID variable

SPATIALID

 

Item Store Control Options

   

Displays the contents of the item store

SHOW

 

Stores the model in an item store

STORE

 

Restores the model from the item store

COUNTREG

RESTORE=

Printing Control Options

   

Prints the correlation matrix of the estimates

MODEL

CORRB

Prints the covariance matrix of the estimates

MODEL

COVB

Prints a summary iteration listing

MODEL

ITPRINT

Suppresses the normal printed output

COUNTREG

NOPRINT

Requests all printing options

MODEL

PRINTALL

Option Process Control Options

   

Specifies maximum number of iterations allowed

MODEL

MAXITER=

Selects the iterative minimization method to use

COUNTREG

METHOD=

Sets boundary restrictions on parameters

BOUNDS

 

Sets initial values for parameters

INIT

 

Sets linear restrictions on parameters

RESTRICT

 

Sets the number of threads to use

PERFORMANCE

 

Specifies the optimization options

NLOPTIONS

See Chapter 7: Nonlinear Optimization Methods

Model Estimation Options

   

Specifies the dispersion variables

DISPMODEL

 

Specifies the type of model

COUNTREG

DIST=

Specifies the type of covariance matrix

MODEL

COVEST=

Specifies the type of error components model for panel data

MODEL

ERRORCOMP=

Suppresses the intercept parameter

MODEL

NOINT

Specifies the offset variable

MODEL

OFFSET=

Specifies the parameterization for the Conway-Maxwell-Poisson (CMP) model

MODEL

PARAMETER=

Specifies the zero-inflated offset variable

ZEROMODEL

OFFSET=

Specifies the zero-inflated link function

ZEROMODEL

LINK=

Specifies variable selection

MODEL

SELECT=( )

Specifies variable selection

DISPMODEL

SELECT=( )

Specifies variable selection

ZEROMODEL

SELECT=( )

Specifies the spatial effects to be added to MODEL statement

SPATIALEFFECTS

 

Specifies variable selection

SPATIALEFFECTS

SELECT=( )

Specifies the spatial effects for dispersion

SPATIALDISPEFFECTS

 

Specifies variable selection

SPATIALDISPEFFECTS

SELECT=( )

Specifies the spatial effects for zero-inflation

SPATIALZEROEFFECTS

 

Specifies variable selection

SPATIALZEROEFFECTS

SELECT=( )

Bayesian MCMC Options

  

Controls the aggregation of multiple posterior chains

BAYES

AGGREGATION=

Automates the initialization of the MCMC algorithm

BAYES

AUTOMCMC()

Specifies the initial values of the MCMC algorithm

INIT

 

Requests evaluation of the marginal likelihood

BAYES

MARGINLIKE

Specifies the maximum number of tuning phases

BAYES

MAXTUNE=

Specifies the minimum number of tuning phases

BAYES

MINTUNE=

Specifies the number of burn-in iterations

BAYES

NBI=

Specifies the number of iterations during the sampling phase

BAYES

NMC=

Specifies the number of threads to use during the sampling phase

BAYES

NTRDS=

Specifies the number of iterations during the tuning phase

BAYES

NTU=

Controls options for constructing the initial proposal covariance matrix

BAYES

PROPCOV=

Specifies the sampling scheme

BAYES

SAMPLING=

Specifies the random number generator seed

BAYES

SEED=

Prints the time required for the MCMC sampling

BAYES

SIMTIME

Controls the thinning of the Markov chain

BAYES

THIN=

Bayesian Summary Statistics and Convergence Diagnostics

Displays convergence diagnostics

BAYES

DIAGNOSTICS=

Displays summary statistics of the posterior samples

BAYES

STATISTICS=

Bayesian Prior and Posterior Samples

Specifies a SAS data set for the posterior samples

BAYES

OUTPOST=

Bayesian Analysis

  

Specifies normal prior distribution

PRIOR

NORMAL (MEAN=, VAR=)

Specifies gamma prior distribution

PRIOR

GAMMA (SHAPE=, SCALE=)

Specifies inverse gamma prior distribution

PRIOR

IGAMMA (SHAPE=, SCALE=)

Specifies uniform prior distribution

PRIOR

UNIFORM (MIN=, MAX=)

Specifies beta prior distribution

PRIOR

BETA (SHAPE1=, SHAPE2=,
MIN=, MAX=)

Specifies t prior distribution

PRIOR

T (LOCATION=, DF=)

Output Control Options

   

Includes covariances in the OUTEST= data set

COUNTREG

COVOUT

Outputs the estimates of dispersion for the CMP model

OUTPUT

DISPERSION

Outputs the estimates of $\mathbf{g}_{i}’\bdelta $ for the CMP model

OUTPUT

GDELTA=

Outputs the estimates of $\lambda $ for the CMP model

OUTPUT

LAMBDA=

Outputs the estimates of $\nu $ for the CMP model

OUTPUT

NU=

Outputs the estimates of $\mu $ for the CMP model

OUTPUT

MU=

Outputs the estimates of mode for the CMP model

OUTPUT

MODE=

Outputs the probability that the response variable will take the current value

OUTPUT

PROB=

Outputs probabilities for particular response values

OUTPUT

PROBCOUNT( )

Outputs the expected value of the response variable

OUTPUT

PRED=

Outputs the estimates of variance for the CMP model

OUTPUT

VARIANCE=

Outputs estimates of $\mathbf{x}_{i}’\bbeta $

OUTPUT

XBETA=

Outputs estimates of $\mathbf{z}_{i}’\bgamma $

OUTPUT

ZGAMMA=

Outputs the probability that the response variable will take a zero value as a result of the zero-generating process

OUTPUT

PROBZERO=

Specifies the output data set for scoring

SCORE

OUT=

Outputs the estimates of dispersion for the CMP model

SCORE

DISPERSION

Outputs the estimates of $\mathbf{g}_{i}’\bdelta $ for the CMP model

SCORE

GDELTA=

Outputs the estimates of $\lambda $ for the CMP model

SCORE

LAMBDA=

Outputs the estimates of $\nu $ for the CMP model

SCORE

NU=

Outputs the estimates of $\mu $ for the CMP model

SCORE

MU=

Outputs the estimates of mode for the CMP model

SCORE

MODE=

Outputs the probability that the response variable will take the current value

SCORE

PROB=

Outputs probabilities for particular response values

SCORE

PROBCOUNT( )

Outputs expected value of response variable

SCORE

PRED=

Outputs the estimates of variance for the CMP model

SCORE

VARIANCE=

Outputs estimates of $\mathbf{x}_{i}’\bbeta $

SCORE

XBETA=

Outputs estimates of $\mathbf{z}_{i}’\bgamma $

SCORE

ZGAMMA=

Outputs the probability that the response variable will take a value of zero as a result of the zero-generating process

SCORE

PROBZERO=