The HPCOUNTREG Procedure
-
Overview
- Getting Started
-
Syntax
-
DetailsMissing ValuesPoisson RegressionConway-Maxwell-Poisson RegressionNegative Binomial RegressionZero-Inflated Count Regression OverviewZero-Inflated Poisson RegressionZero-Inflated Conway-Maxwell-Poisson RegressionZero-Inflated Negative Binomial RegressionParameter Naming Conventions for the RESTRICT, TEST, BOUNDS, and INIT StatementsComputational ResourcesCovariance Matrix TypesDisplayed OutputOUTPUT OUT= Data SetOUTEST= Data SetODS Table Names
-
Examples
- References
Missing Values
Any observations in the input data set that have a missing value for one or more of the regressors are ignored by PROC HPCOUNTREG and not used in the model fit. PROC HPCOUNTREG rounds any positive noninteger count values to the nearest integer and ignores any observations that have a negative count.
If the input data set contains any observations that have missing response values but nonmissing regressors, PROC HPCOUNTREG
can compute several statistics and store them in an output data set by using the OUTPUT statement. For example, you can request
that the output data set contain the estimates of 
, the expected value of the response variable, and the probability that the response variable will take the current value.
Furthermore, if a zero-inflated model was fit, you can request that the output data set contain the estimates of 
, and the probability that the response is 0 as a result of the zero-generating process. Note that the presence of such observations
(that have missing response values) does not affect the model fit.