The following features have been added to the HPSEVERITY procedure :
The HPSEVERITY procedure now supports the CLASS statement and specification of a wide variety of regression effects in the SCALEMODEL statement. These include singleton continuous effects, polynomial continuous effects, main CLASS variable effects, interaction effects, nested effects, continuous-by-class effects, continuous-nesting-class effects, and a general combination of the preceding effects.
Note that when you specify regression effects that contain interactions or CLASS variables, the OUTSCORELIB statement and the INEST= option are not supported.
The HPSEVERITY procedure now supports a new method of saving the estimation results and using them for parameter initialization. The new OUTSTORE= option creates an item store, which is a binary file in a format that is specific to the SEVERITY and HPSEVERITY procedures. You can use an OUTSTORE= item store that is created in one PROC SEVERITY or PROC HPSEVERITY step to initialize the parameters in a subsequent PROC SEVERITY or PROC HPSEVERITY step by specifying the new INSTORE= option. These options are required if you want to save and initialize a scale regression model that contains interaction effects or effects with CLASS variables.
Both the OUTSTORE= and INSTORE= options are experimental in this release of the HPSEVERITY procedure.
The OUTSCORELIB statement to create scoring functions, which was introduced in the previous version of PROC HPSEVERITY, is now at production status. Note that the scoring functions are not supported when you specify a scale regression model that contains interaction effects or effects with CLASS variables.
The HPSEVERITY procedure now supports the options that were previously available only in the SEVERITY procedure. These include the following:
You can specify the PLOTS= option in the single-machine mode of execution. You can request the individual and comparative plots of cumulative distribution functions (CDF) and probability density functions (PDF) of all candidate distributions. You can also request the P-P and Q-Q plots for individual candidate distributions. The individual CDF plots also contain the upper and lower confidence limits of the empirical distribution function (EDF) estimates. You can use the new EDFALPHA= option to control the plotted EDF confidence limits.
You can specify the OUTCDF= option to create a SAS data set in the single-machine mode of execution. This data set contains the EDF estimates and CDF estimates of all distributions that do not fail to converge.
You can specify the PROBOBSERVED= suboption of the LEFTTRUNCATED= option in the LOSS statement. This option enables you to specify the probability of observability, which is defined as the probability that the underlying severity event is observed (and recorded) for the specified left-threshold value.
The set of options that you can specify in the NLOPTIONS statement is now identical to the set of options that are available in PROC SEVERITY.