The QUANTREG Procedure

The OUTEST= data set contains parameter estimates for the specified model with all quantiles. A set of observations is created for each quantile specified. You can also specify a label in the MODEL statement to distinguish between the estimates for different models used by the QUANTREG procedure.

Note that, if the QUANTREG procedure does not produce valid solutions, the parameter estimates are set to missing in the OUTEST data set.

If created, this data set contains all variables specified in the MODEL statement and the BY statement. Each observation consists of parameter values for a specified quantile with the dependent variable having the value .

The following variables are also added to the data set:

_MODEL_

a character variable of length 8 containing the label of the MODEL statement, if present. Otherwise, the variable’s value is blank.

_ALGORITHM_

a character variable of length 8 containing the name of the algorithm used for computing the parameter estimates, either SIMPLEX, INTERIOR, or SMOOTH

_TYPE_

a character variable of length 8 containing the type of the observation. it is fixed as PARMS to indicate that the observation includes parameter estimates.

_STATUS_

a character variable of length 12 containing the status of model fitting, either NORMAL, NOUNIQUE, or NOVALID

Intercept

a numeric variable containing the intercept parameter estimates

_QUANTILE_

a numeric variable containing the specified quantile levels

Any BY variables specified are also added to the OUTEST= data set.